hipocampo

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are present, so the description carries full responsibility for behavioral disclosure. It only states that a directory is added to the watch list but does not mention side effects, idempotency, duplicate handling, permission requirements, or whether reindexing starts immediately.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single efficient sentence with no filler. The core action and purpose are front-loaded and every word contributes meaning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given this is a simple one-parameter tool with an output schema, the description is adequate for basic invocation. However, with no annotations, it lacks details about behavioral side effects and edge cases such as duplicate directories or invalid paths.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It clarifies that 'path' refers to a directory, which adds meaning beyond the raw schema, but it does not specify path format, existence requirements, or whether relative/absolute paths are accepted.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Agrega') and resource ('directorio al watch list') and explains the purpose ('para auto-reindexación'). It clearly differentiates this from siblings like remove_watch_dir and list_watch_dirs.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies the tool is for adding directories to be watched for auto-reindexing, but it does not explicitly state when to prefer it over similar siblings or mention any exclusions. The use case is inferable but not explicitly guided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full responsibility for behavioral disclosure. It thoroughly explains that the tool first searches Hipocampo, then compresses top-k results, describes method-specific behavior (e.g., API costs, quality differences, hybrid's content-based routing), and lists return values including compression statistics. This exceeds typical transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with a clear intro, method bullets, a usage case, Args, and Returns sections. Every sentence adds value, and the format is easy to scan. It is not overly verbose despite covering complex behavior.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description is complete for an agent to select and invoke the tool: it explains the search+compress flow, method choices, parameter effects, and return format. It even includes output details despite the presence of an output schema, making standalone comprehension straightforward.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description fully compensates with an 'Args' section explaining each parameter's meaning and defaults (e.g., 'k: Number of memories to retrieve (default 5, max 20)', 'target_token: Target token count (-1 = auto...)'). Parameter semantics are significantly enriched beyond the bare schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: 'Compress retrieved memories using a hybrid approach (extractive + LLM)' and explicitly connects it to the workflow ('Use this tool BEFORE sending context to another LLM'). It distinguishes itself from sibling search tools by focusing on compression with retrieval, making its purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit guidance on when to use the tool ('Use this tool BEFORE sending context to another LLM to reduce prompt size') and details method selection (extractive, llm, hybrid) with tradeoffs. It lacks explicit 'when not to use' or alternative tool references, but the provided context is sufficient for most decisions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses the core behavior (searching, promoting, optional compression) and dry_run functionality, which is valuable given no annotations exist. However, it does not clarify whether the original episodic memories are deleted or preserved, nor the details of compression. This leaves uncertainty about side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is succinct and well-structured with a title, behavior explanation, and Args/Returns sections. Every sentence adds value, and there is no redundant information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the main function and parameters, and the presence of an output schema mitigates the need for detailed return info. However, it omits side effects (e.g., whether original memories are removed) and prerequisites, leaving gaps for an agent considering this mutation tool. Given its moderate complexity, it is adequate but not fully complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description adds clear semantics for both parameters: min_age_days is 'la edad mínima en días para consolidar' with default 7, and dry_run is explained as showing only what would be consolidated. This directly supplements the schema, which has no property descriptions, making the tool usable.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: 'migra memorias episódicas antiguas a semánticas' (migrates old episodic memories to semantic). This specific verb+resource structure distinguishes it from siblings like compress_hipocampo or set_nivel_hipocampo, which perform different operations.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no explicit guidance on when to use this tool versus alternatives like compress_hipocampo or set_nivel_hipocampo. It describes the process but lacks exclusions or preferred contexts. This leaves the agent to infer usage from the described behavior.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the behavioral burden, and it explains the negation-probe embedding method, the comparison, and the distance-based contradiction signal. The algorithm strongly implies a read-only detection operation, though side effects are not explicitly addressed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and front-loaded: purpose, method, decision criterion, then arguments. Every sentence contributes useful information without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simple one-parameter interface, the existence of an output schema, and no annotations, the description covers the tool's purpose, invocation parameter, and behavioral mechanism. Nothing is missing for an agent to select and call it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, but the description compensates by documenting memory_id as the numeric ID of the memory in memoria_vectorial. This adds real meaning beyond the integer type in the schema and is sufficient for the single required parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Detecta contradicciones semánticas de una memoria existente.' This clearly identifies a unique detection task separate from the sibling search, update, and maintenance tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The context is clear: use this tool when you have a memory_id and need to check an existing memory for semantic contradictions. It does not explicitly name when-not-to-use alternatives, but the unique purpose and required memory_id make the intended usage evident.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and largely succeeds: it discloses destructive effects (eliminating links < 0.01, archiving memories), a safety default (dry_run true means read-only), and explicit protected categories. It slightly underplays permanence/reversibility implications and does not explain what 'archives' means operationally, so it is not a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well organized into a one-line summary followed by compact sections for links, memories, protections, args, and returns. Front-loaded with purpose and zero filler, every sentence carries operational information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter, no-annotation tool with an output schema, the description is complete: it covers target scope, thresholds, exclusions/protections, dry-run safety, and return value at a high level. The output schema removes the need to detail the report shape.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate for the two parameters. It does: dry_run is explained as read-only vs. executing changes, and min_age_days is defined as the minimum age in days for a memory candidate. Minor gaps remain (whether min_age_days applies to links as well, inclusivity of the boundary), so not a 5.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific action ('Aplica decaimiento temporal') on a concrete resource set (graph links and old memories), and details exact behavior for each (exponential weight decay, half-life, eliminating links < 0.01, archiving episodic memories). This is clearly differentiated from sibling operations like delete_hipocampo, consolidate_hipocampo, or hipocampo_maintenance.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The intended context is implied: use decay_hipocampo to age out old graph links and archive eligible memories. However, it does not explicitly state when to prefer it over sibling tools such as hipocampo_maintenance, consolidate_hipocampo, compress_hipocampo, or delete_hipocampo, nor does it give any when-not-to-use conditions beyond the listed protections.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden of disclosure. It explicitly states the irreversible nature and consequences of deletion ('Esta operación es irreversible. Una vez eliminado, el recuerdo no podrá recuperarse ni aparecerá en búsquedas futuras.'). However, it does not disclose what happens if the ID does not exist or any required permissions, leaving some behavioral aspects implicit.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and well-structured, starting with a clear main statement, followed by an important caution, and then organized Args and Returns sections. Every sentence contributes essential details without unnecessary filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a single-parameter delete operation, the description covers purpose, irreversibility, parameter semantics, and return type. Since an output schema is present, detailed return structure is not required. A minor gap is the lack of behavior for a non-existent ID, but overall the tool is adequately described.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 0% description coverage, but the description compensates fully by explaining the 'id' parameter as 'ID numérico del recuerdo a eliminar.' This adds meaning beyond the schema's simple integer type, clearly identifying what the ID represents and how it is used.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: 'Elimina un recuerdo del Hipocampo (memoria_vectorial) por su ID.' This specifies the verb, resource, and method of operation, and it naturally distinguishes itself from sibling tools like search_hipocampo, update_hipocampo, and decay_hipocampo.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use the tool by emphasizing that the operation is irreversible and the memory cannot be recovered or appear in future searches. This provides clear context for permanent deletion, but it does not explicitly mention alternatives or when not to use it compared to siblings, such as decay_hipocampo for non-destructive adjustments.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It discloses the return format (ASCII tree), parameter limits (depth max 5, max_nodes default 50), and node_id=0 behavior. However, it does not explicitly state that the operation is read-only or describe potential side effects or errors.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise, with a clear initial sentence, structured args section, and returns section. Every line earns its place with no redundancy or unnecessary text.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a graph exploration tool, the description adequately covers parameters and return format. It lacks usage alternatives and does not explicitly state read-only behavior, but given the output schema and 0% schema coverage, it is reasonably complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

All three parameters are fully explained beyond the schema, including defaults, max constraints, and special behavior for node_id=0. This fully compensates for the 0% schema description coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool explores the memory graph from a root node and returns an ASCII tree. It is specific and distinguishable from siblings like search_hipocampo, though it doesn't explicitly name alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is given on when to use this tool versus alternatives like search_hipocampo or path_hipocampo. It mentions the special case of node_id=0 for overview but doesn't provide context or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description outlines the tool's actions (restarting PostgreSQL, creating tables, verifying a key) and states it returns a report. Since no annotations are provided, the description carries the full burden. It is adequate but could be improved by indicating that operations like restarting PostgreSQL may cause temporary unavailability or that the tool attempts repairs but does not guarantee success.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and well-structured. It starts with a one-sentence purpose, then uses a bullet list for repair actions, and ends with the return type. Every part is informative without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given that there are no parameters and an output schema exists, the description covers the essential aspects: what repairs are attempted and what is returned. However, it could be more complete by explaining how the tool detects issues (e.g., from 'hipocampo_health'?) or when an agent should invoke it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has zero parameters, so the schema already fully defines the interface. The description adds value by listing the specific repair actions, giving an agent context on what the tool will do with no input. This aligns with the baseline of 4 for no-parameter tools.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Intenta reparar automáticamente problemas detectados en el sistema' (attempts to auto-repair detected system issues). It enumerates specific repairs like restarting PostgreSQL, creating missing tables, and verifying NVIDIA_API_KEY. However, it does not differentiate itself from siblings like 'hipocampo_health' or 'hipocampo_maintenance', which could overlap in functionality.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no explicit guidance on when to use this tool versus alternatives. It lists possible repairs but does not specify prerequisites, conditions for use, or scenarios where it should be avoided. Sibling tools like 'hipocampo_health' or 'hipocampo_maintenance' might be more appropriate in certain contexts, but no comparison is made.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure and does it well: it explains the HOT/WARM/COLD states, that COLD content is moved to memoria_historica and removed from main search, and that protected categories are exempt. It does not mention reversibility or authorization requirements, but the main side effects are clearly stated.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact, well-organized, and front-loaded. The purpose, tier definitions, exemptions, and parameter behavior are each given clear sections without redundant prose. Every sentence contributes meaningful information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the core behavior, tier mechanics, exemptions, and the only parameter thoroughly. Since an output schema exists, return-value documentation is not required. It could optionally explain budget thresholds or what triggers automatic tiering, but the provided context is sufficient for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% and the schema only provides type/default for dry_run. The description fully compensates by explaining that True is the default and means 'analysis only', while False executes the tiering. This is complete, unambiguous parameter semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states a specific action ('Gestiona el presupuesto de memoria') and defines the underlying tiering mechanism with HOT/WARM/COLD categories. It distinguishes the tool's domain from general maintenance or search tools, though it does not explicitly name sibling alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The dry_run parameter is explained with actionable guidance: use True for analysis only and False to execute tiering. It also specifies that protected entries are exempt, which helps the agent decide what will be affected. However, it does not explicitly state when to prefer this tool over sibling tools like hipocampo_maintenance or compress_hipocampo.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, but the description fully discloses safety: dry_run=true is read-only, dry_run=false is destructive and irreversible (original files deleted). It also states idempotency, which adds important behavior beyond the schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with paragraphs for safety, usage, and args/returns sections. Every sentence adds value, from the log-checkpointing concept to the periodic maintenance recommendation.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter tool with an output schema, the description is complete: it explains purpose, usage context, behavioral safety, parameter effect, and return value (report with count and freed space). No gaps remain.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

While input schema only defines dry_run as a boolean with default, the description explains the semantic difference: True shows what would be compressed, False executes irreversible compression. This fully compensates for the 0% schema description coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states 'Comprime memorias antiguas usando checkpointing logarítmico' with a specific verb and resource. It also distinguishes from hipocampo_maintenance by noting this tool is for standalone execution or preview, giving clear sibling differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly says 'Para ejecutar checkpoint como parte del ciclo completo de mantenimiento, usar hipocampo_maintenance (paso 3 del ciclo). Esta herramienta es para ejecución puntual o previsualización.' This gives a clear when-to-use and alternative.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description discloses that merge=False is read-only and safe, while merge=True is destructive and irreversible. It also defines what constitutes a duplicate (embedding+text similarity above 0.95) and outlines report contents, providing behavioral context beyond the schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured into short paragraphs: purpose, safety modes, definition, report contents, and usage guidance. Every sentence adds distinct value with no redundancy, making it appropriately sized.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a single-parameter tool with an output schema, the description covers purpose, safety, duplicate definition, report contents, and relationship to sibling tools. It leaves no significant gaps for an agent to invoke and interpret results.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The only parameter 'merge' is fully explained in the description: False (default) is analysis-only and True merges irreversibly. Since the schema provides no description for the parameter, this explanation fills the gap entirely.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description states 'Detecta y opcionalmente fusiona duplicados en las tablas de memoria' – a clear verb+resource. It further distinguishes from hipocampo_maintenance by noting this tool is for 'uso puntual o previsualización antes del merge', which differentiates it from that sibling.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly says 'Para ejecutar dedup como parte del ciclo completo de mantenimiento, usar hipocampo_maintenance' and advises 'Ejecutar primero sin merge para previsualizar', giving clear when-to-use and when-not-to-use guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It lists checked components and states a formatted report is returned, suggesting a read-only operation, but does not explicitly confirm no side effects, authentication needs, or failure behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise with two sentences, a bullet list, and a clear return statement. Every part is necessary and front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given zero required parameters and an existing output schema, the description covers the tool's purpose, checks, and output format adequately. It lacks details on execution mode (sync/async) or error handling, but is sufficient for its simplicity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

No parameters exist, so the description does not need to elaborate. The baseline is 4 for zero-parameter tools, and the description adds context about what the health check verifies, which is acceptable.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it executes a complete health check of the Hipocampo system, lists specific components checked (PostgreSQL, NVIDIA API, tables, disk space, extensions), and mentions the return format. This distinguishes it from siblings like hipocampo_auto_repair.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool versus alternatives. The purpose implies it's for health checks, but there is no mention of when not to use it or which sibling to choose for specific tasks.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden of behavioral disclosure. It discloses concrete side effects for each step: auto-repair if needed, merges duplicates, compresses old memories, purges access logs >30d, and adjusts thresholds. It also states the return value is a consolidated report. It doesn't mention whether the overall operation is reversible or if confirmation is required, but the enumerated behaviors provide solid transparency for a maintenance tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-organized: a header sentence, a numbered list of steps, a cautionary note, and a return statement. Every sentence earns its place, with no redundancy or extraneous detail. The structure makes it easy to scan and parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter tool with an output schema, the description covers the full behavior, including sub-steps, exclusions, and return value. It clearly separates this tool from two destructive sibling operations. There are no missing prerequisites, parameters, or critical caveats needed for an agent to invoke it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has zero properties and schema description coverage is 100%, so there are no parameters to document. Per the zero-parameter baseline, the description need not add parameter semantics. The description focuses on behavior, which is appropriate here.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states 'Ejecuta el ciclo completo de mantenimiento' and enumerates five concrete steps (health check, dedup, checkpoint, purge, tune), each mapping to specific behaviors. It clearly distinguishes itself as the composite maintenance operation, and the note about budget/decay reinforces what the tool is not. This is a specific verb+resource with strong sibling differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly lists the maintenance steps and then provides a cautionary note: 'hipocampo_budget y decay_hipocampo se ejecutan manualmente o via cron separado (son destructivos y requieren dry_run previo).' This tells the agent when to use this tool (full maintenance cycle) and when not to use it for those destructive operations, naming the alternatives directly. It gives clear context and exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must disclose behavioral traits. It mentions analyzing stats and giving recommendations but does not specify if the tool is read-only, requires authentication, or has rate limits. The behavioral profile is incomplete.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise, with a clear opening statement and bullet-like details. Every sentence contributes meaningful information, and it is appropriately front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no parameters and an existing output schema, the description adequately covers the tool's purpose and return values. It is complete for a statistics-gathering tool with no inputs.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has no parameters, so the baseline is 4. The description adds value by detailing what is analyzed (latency, methods, average scores) and the output (report with recommendations), which goes beyond the empty input schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool shows performance statistics and analysis of queries, methods, and scores, and provides optimization recommendations. It differentiates from sibling tools like health, tune, etc., by focusing on performance metrics.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for performance analysis but does not explicitly state when to use this tool versus alternatives like hipocampo_health or hipocampo_tune. No exclusions or contextual advice are provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It openly states that the tool is destructive ('modifica los thresholds y pesos de forma irreversible') and idempotent ('ejecutarlo múltiples veces converge al mismo resultado'), and advises caution. This is substantial transparency beyond the bare minimum.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and well-structured. It front-loads the main purpose, then adds safety warnings, alternative tools, and specific usage conditions. Each sentence contributes value, with no redundant information. The length is appropriate given the destructive nature of the tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers all essential aspects: what the tool does, its irreversible side effects, when to use it, when not to use it, alternatives, and what it returns. Given the empty input schema and presence of an output schema, this is complete. It effectively compensates for missing annotations by providing all necessary behavioral context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero input parameters, so the baseline score is 4. The description does not need to document parameter semantics, as there are none. It briefly mentions the internal 'thresholds y pesos' being tuned, which adds context but is not required for parameter understanding.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: 'Ajusta automáticamente los thresholds y pesos del SSC basado en las métricas de rendimiento acumuladas.' It uses a specific verb and resource, and explicitly distinguishes itself from siblings like hipocampo_stats (read-only) and hipocampo_maintenance (full cycle). This makes the purpose unambiguous and well-differentiated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit guidance on when to use and when not to use: 'Recomendado ejecutar solo después de acumular suficientes métricas (al menos 100 consultas registradas)' and 'No usar si el sistema funciona correctamente sin degradación.' It also names alternatives: hipocampo_stats for read-only viewing and hipocampo_maintenance for the full maintenance cycle, giving clear context and exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the transparency burden. It discloses that it scans specific file types, creates memory embeddings, and supports incremental updates. It does not detail all side effects like overwriting existing memories, but provides substantial behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with a clear intro, incremental behavior note, args, and returns sections. Each sentence provides necessary information without unnecessary verbosity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the core functionality, parameters, and incremental logic. It does not explain potential edge cases like ignored directories or interaction with other Hipocampo tools, but given the output schema exists, the return value is adequately specified.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, and the description fully compensates by explaining both parameters: project_path defaults to the current directory, and force triggers a full re-index. This adds meaning beyond the schema's type/default fields.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool indexes source code files into Hipocampo RAG, specifying file types and the chunking/embedding process. This distinguishes it from sibling tools like search_code or save_hipocampo.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides usage context by explaining the incremental mtime-based behavior on second runs and the purpose of the force parameter. However, it does not explicitly mention alternatives or exclusions relative to sibling tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must fully disclose behavioral traits. While it states the action (creating a link) and the return value (confirmation), it does not mention potential side effects, whether the operation is destructive, if existing links are replaced, or any permission requirements. This is insufficient for a mutation tool without annotation support.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and well-structured: a one-sentence summary followed by an Args list and a Returns note. Each piece of information is useful and not redundant with the schema, given the schema lacks descriptions. It could be slightly tighter by moving the relation_type values to the schema, but the current format is efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 4 parameters and an output schema, the description covers all necessary aspect: what it does, all arguments, and the return type. The parameter explanations are thorough, and the return value is stated as a confirmation. The only missing context is edge-case behavior (e.g., invalid IDs, duplicate links), but given the simplicity and output schema, this is acceptable.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description adds substantial meaning beyond the raw schema. It explains each parameter: source_id and target_id with their types (numeric vs string), relation_type with common values and the default 'related', and weight with a valid range and default. This fully compensates for the schema's 0% description coverage, making the parameters clear and actionable.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Crea un enlace entre dos recuerdos en el grafo de memoria' (Creates a link between two memories in the memory graph). This is a specific verb+resource combination that is easy to understand. However, it does not explicitly distinguish itself from related sibling tools like unlink_hipocampo, so it lacks sibling differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It only defines what the tool does, without mentioning appropriate contexts, exclusions, or references to alternative tools. This leaves the agent to infer usage from the tool's name and purpose.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It accurately conveys a read-only listing operation, but it does not explicitly state that it makes no changes or how the configured directories are sourced; the output schema presumably covers the return shape.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, tightly written sentence that front-loads the action and object. Every word contributes to the meaning, and there is no redundant or filler content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a no-parameter listing tool with an output schema, the description is largely adequate. However, the sibling set contains several watch-related tools such as list_watches and watch_hipocampo, and the definition does not disambiguate when list_watch_dirs is the appropriate choice.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so there is no parameter ambiguity to resolve. With an empty properties schema and 100% schema coverage, the description does not need to add parameter-level meaning, and the baseline of 4 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states the verb 'Lista' and the specific resource 'directorios configurados para auto-reindexación', making the tool's function clear. It is distinguishable from similar siblings like list_watches by the auto-reindexation scope, though it does not explicitly name or contrast that sibling.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance is given about when to use this tool versus list_watches, add_watch_dir, remove_watch_dir, or watch_hipocampo. The phrase 'para auto-reindexación' implies a context, but there is no direct when-to-use or when-not-to-use statement.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. The phrase 'Lista todos' indicates a read-only action, but it does not explicitly state the absence of side effects, authentication needs, or any other behavioral traits such as pagination or ordering. The description adds minimal context beyond the obvious.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise, using two short sentences and a return list. Every word adds value: it states the action, the object (webhooks), and the return format (ID, pattern, URL). No redundancy or unnecessary detail.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (zero parameters) and the presence of an output schema, the description fully covers the tool's purpose and expected return. It is complete and self-contained, making it easy for an agent to invoke correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters and the schema is fully covered by the empty properties object. Per the rubric, a zero-parameter tool baselines at 4, and the description correctly omits any parameter details since none exist.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states that the tool lists all registered webhooks ('Lista todos los webhooks registrados') and specifies the return fields (ID, pattern, URL). This is a specific verb+resource combination that differentiates it from sibling tools like watch_hipocampo (which adds a watch) and unwatch_hipocampo (which removes one).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for retrieving all webhooks but does not explicitly state when to use this tool versus alternatives, nor does it mention any exclusions or prerequisites. For a simple listing tool, the context is somewhat clear, but explicit guidance is missing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must carry behavioral disclosure. It provides useful limits (max_depth default/max) and return format, but it does not mention whether the operation is read-only, what happens when no path exists, or any side effects. It offers some behavioral context but has gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and well-structured: a one-sentence purpose, then parameter definitions, then return statement. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

While the description covers purpose, parameters, and return value (and an output schema exists), it leaves important behavior unstated, such as behavior when no path is found, whether max_depth is inclusive, and whether the graph is weighted. For a pathfinding tool, these are significant gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema provides only types and titles with zero description coverage. The description compensates fully by defining each parameter: from_id (origin memory), to_id (destination memory), and max_depth with default and max. This adds essential semantic meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool finds the shortest path between two memories in the memory graph, naming the specific resource and operation. However, it does not explicitly distinguish it from sibling search tools, so it misses the top score.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies the tool should be used when a shortest path between two memory nodes is needed, but it provides no explicit guidance on when to prefer this over sibling tools like search_hipocampo or graph_hipocampo.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. It discloses the extraction and compression behavior, and the default path behavior for project_path. However, it does not explicitly state whether the operation is read-only or if there are any side effects, permissions, or prerequisites, leaving some ambiguity for such a memory-related tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and well-structured: opening purpose sentence, a usage guideline sentence, a clear Args list, and a Returns statement. Every sentence serves a purpose with no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is simple (2 optional params, no required), and the description covers purpose, usage, parameters, and return value. It does not discuss error cases, prerequisites like existing memories, or permissions, but for a read-like preload operation this is reasonably complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, but the description fully compensates with a dedicated 'Args' section explaining both parameters: project_path (absolute path, defaults to cwd) and k (number of memories, default 8, max 20). This adds meaning far beyond the bare schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: 'Pre-load context for a project or workspace' and 'Extracts relevant memories... returns them as a compressed summary.' It uses a specific verb and resource, and the phrase 'starting work on a known project to restore working context' distinguishes it from sibling search tools (e.g., search_hipocampo).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly says 'Use this when starting work on a known project to restore working context,' providing a clear usage context. It does not mention exclusions or alternative tools, but the context is specific enough to guide selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the burden of behavioral disclosure. It explains that the tool saves data in memory_items and the type of data, but it does not mention whether updates overwrite or append, or any side effects. For a basic save operation, the explanation is adequate but lacks depth.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two paragraphs with front-loaded purpose and differentiation. It is efficient but slightly verbose with the Spanish phrasing; however, every sentence adds value. Minor improvement could be more brevity, but overall well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has 3 parameters, no enums, and an output schema (implied by the return description). The description covers usage, parameter semantics, and return value ('Confirmación con el ID asignado'). For a simple save tool, it is complete and leaves no critical gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 0% description coverage, so the description must compensate. It fully explains each parameter: summary as a short personal data text with an example, extra as optional additional plain text, and categories as optional categories with an example. This adds significant meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool saves personal profile data in Hipocampo's memory_items. It uses a specific verb ('guarda') and resource ('dato de perfil personal'), and explicitly distinguishes it from the sibling save_hipocampo, which stores technical vector memory.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit when-to-use guidance by contrasting with save_hipocampo, noting that this tool is for personal data (gustos, familia, preferencias, datos biográficos). It clearly indicates the context where this tool should be chosen over its sibling.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description fully carries the transparency burden. It states the tool is read-only, has no side effects, and behaves identically to search_hipocampo. It also describes the return format as plain text with relevance scores and metadata, which is rich behavioral disclosure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with clear sections for behavior, usage, args, and returns. While somewhat verbose, every sentence contributes useful information, and the organization makes it easy to scan. Minor redundancy exists between 'Comportamiento y salida idénticos' and 'Mismo formato...'.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is an alias, and the description fully covers purpose, when to use it, behavior, parameters, and return format. It appropriately references search_hipocampo for the full behavior, which is acceptable given the alias relationship. There is no output schema shown, but the return description is sufficient.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has no descriptions for the parameters. The description compensates by explaining that 'query' is natural language search text with examples, and 'session_id' is optional to filter to a specific session. This adds significant meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states this is a quick search tool in Hipocampo and explicitly identifies it as a short alias for search_hipocampo. The verb 'search' and resource 'Hipocampo' are specific, and it distinguishes itself from other sibling tools by referencing the canonical tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly tells when to use this tool: when the MCP client prefers shorter tool names. It also directs to the alternative, search_hipocampo, for a more descriptive name. This provides clear when/alternative guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No hay anotaciones, así que la descripción es la única fuente de comportamiento. 'Fuerza reindexación inmediata' y '(o todos los watch)' comunican que la operación es forzosa, inmediata y puede abarcar todos los watch, pero no se mencionan efectos secundarios, coste o si requiere permisos específicos.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Una sola frase sin palabras de relleno. La información principal (acción forzosa, inmediatez, alcance directorio/todos los watch) está al frente y cada elemento aporta.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Para una herramienta de un solo parámetro opcional con output schema, la descripción es casi suficiente a nivel de invocación: define qué reindexa y el alcance. Falta aclarar si el directorio debe ser un watch existente, qué ocurre con una ruta inválida, y no hay guía de uso frente a herramientas hermanas.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Con 0% de cobertura en el schema, la descripción compensa en parte: indica que la operación se aplica a un directorio y que, en lugar de un directorio concreto, puede aplicarse a todos los watch, lo que da sentido al path opcional y a su default vacío. No relaciona explícitamente el nombre del parámetro 'path' con ese directorio.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

La descripción usa un verbo concreto ('Fuerza reindexación inmediata') y un recurso específico ('un directorio (o todos los watch)'), por lo que un agente entiende la acción y el alcance. No diferencia explícitamente de herramientas hermanas como hipocampo_maintenance o index_project, por eso no alcanza el 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No indica cuándo usar esta herramienta frente a las alternativas hermanas, ni excluye casos de uso. Solo se puede inferir que el caso de uso es una reindexación inmediata, pero no hay mención de condiciones, prerrequisitos ni cuándo no usarla.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

There are no annotations, so the description carries the full burden of behavioral disclosure. It only says the directory is removed from the watch list; it does not mention whether the operation is persistent, idempotent, or what happens if the path is not currently watched.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single short sentence conveys the core action with no filler or repetition. The essential information is front-loaded and easy to parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple one-parameter tool with an output schema, the description is mostly complete: the agent knows what action to take and what parameter to provide. It would benefit from a little more behavioral context, but the simplicity of the tool keeps the gap small.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It clarifies that 'path' refers to a directory in the watch list, but it does not specify path format, absolute vs relative, or behavior for invalid paths. This is minimal but non-redundant value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Elimina'), a clear resource ('directorio del watch list'), and is immediately distinguishable from sibling tools like add_watch_dir and list_watch_dirs. There is no ambiguity about what the tool does.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The intended use is implied: use this when a directory should no longer be watched. However, the description provides no explicit guidance on when to prefer it over alternatives such as unwatch_hipocampo, nor does it mention prerequisites or edge cases.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must carry behavioral disclosure itself. It does reveal that the embedding is automatically reconstructed and the memory moves to the HOT tier. It does not mention whether the historical copy is deleted, whether the operation is idempotent, or what side effects may occur, leaving some important gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and information-dense: three short sentences convey the action, the source/destination, the automatic embedding reconstruction, and the resulting tier. The Args line is necessary because the schema gives no parameter description, so every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple one-parameter tool with an output schema, the core operation and expected behavior are adequately described. Minor gaps remain, such as failure behavior and whether the source memory is retained or removed, but these are secondary for this low-complexity tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema provides only an integer type with zero description coverage. The description fully compensates by explaining that historica_id is 'ID de la memoria en memoria_historica,' which gives the agent the precise meaning needed to supply this required parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: 'Restaura una memoria desde memoria_historica a memoria_vectorial.' It also adds distinctive behavior details — automatic embedding reconstruction and return to the HOT tier — that clearly separate it from the many hipocampo sibling tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use the tool: when a memory is in memoria_historica and needs to be restored to the HOT tier. However, it provides no explicit alternatives, exclusions, or comparison with related operations like rollback_checkpoint or consolidate_hipocampo.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It explicitly discloses that dry_run=False degrades rules to 'semantica', that rules are not deleted, and that they lose compression immunity. This covers the main side-effects and mutation behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with an intro, explanation, args, and returns. Each sentence serves a purpose; no fluff. The dry-run behavior is repeated in prose and args for clarity, but not excessively.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description explains the rule lifecycle (permanent vs degradable), the condition for degradation (review_count=0 after max_age_days), and the effect of degradation. Since an output schema exists, return values are covered. It is complete for this tool's scope.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must compensate. It clearly explains both parameters: 'max_age_days' as age threshold and 'dry_run' as toggle between listing and actually degrading. This adds meaningful semantics beyond the schema's titles and defaults.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Revisa reglas automatica') and the specific resource ('reglas automatica sin revisión'), and explains the additional degradation behavior. It distinguishes from siblings by focusing on automatica rules and their lifecycle.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Clear context is provided: use this to review automatica rules not reviewed in N days and potentially degrade them if review_count=0. No explicit alternatives or exclusions are mentioned, but the trigger conditions are well-explained.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It discloses the decision logic: checks if originals exist, reports no rollback, or attempts to restore. However, it does not state whether the operation is destructive, any side effects, or failure handling, leaving gaps in transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise, using a brief paragraph and an ordered Args/Returns structure. It provides necessary detail without unnecessary length, though a bit more structure could improve scannability.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a single-parameter tool with an output schema, the description covers the main process and return value. However, absence of annotations means safety/error context is missing, and the description does not explicitly mention permissions or potential failures, leaving completeness slightly incomplete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, but the description defines snapshot_id as 'ID del snapshot [CHECKPOINT SNAPSHOT] guardado,' adding meaningful context beyond the schema's bare integer type. This compensates well for the lack of property descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Revierte un checkpoint usando el snapshot guardado previamente' and details the rollback process. This distinguishes it from sibling tools like compress_hipocampo and delete_hipocampo.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage by explaining when rollback is needed (when original IDs were compressed and deleted), but it does not explicitly mention alternatives or exclusion conditions. It provides context but lacks direct 'when to use' guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and delivers: it discloses that the insert is non-blocking, the embedding is backfilled in background (_finalize_save_bg), the memory is temporarily WARM with embedding=NULL yet text-recoverable, trigram dedup skips unless force=True, semantic dedup >0.9 only logs, and critico grants lifetime protection. This goes far beyond what the schema or annotations would reveal.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The layout is clear: one-line purpose, behavior overview, then labeled Args block and a Returns line. Slight redundancy exists — auto-link and dedup appear both in the opening background-task list and again in the parameter notes — but the length is earned given 9 undocumented parameters in the schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 9-parameter write tool with no annotations and 0% schema description coverage, the description covers purpose, asynchronous behavior, all parameter semantics, dedup edge cases, protection semantics, and the return value (confirmation with assigned ID). The presence of an output schema means return details needn't be spelled out further; little that an agent needs to invoke this correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description fully compensates by documenting all 9 parameters: memory_type with enumerated meanings ('event', 'decision', 'profile'), code/categories with concrete example values, nivel with the three hierarchy levels and their semantics, plus the behavioral meaning of force and auto_link. Every parameter in the schema is explained with meaning beyond its type.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States the verb and resource explicitly: 'Guarda un recuerdo en el Hipocampo (memoria_vectorial)' — save a memory to the vectorial memory store. The opening also distinguishes the behavior (immediate non-blocking INSERT with background embedding) from any read/update sibling, so an agent can tell save_hipocampo apart from search_hipocampo, update_hipocampo, or link_hipocampo.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The usage context is strongly implied — this is the primary write path for persisting a new memory — and it explains when a save is skipped (existing near-identical trigram, unless force=True). However, it never names alternatives or states when-not-to-use, e.g., when to update an existing memory via update_hipocampo rather than re-saving, so the agent must infer sibling differentiation.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden for behavioral disclosure. It details the filtering mechanism (only code_snippet type), the return payload (real code fragments with file location), and parameter constraints (k max 20, language filter). However, it stops short of describing error conditions, authentication requirements, or whether the operation is read-only, which a search tool might safely assume.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and well-structured, using an Args/Returns format. Every sentence adds value: purpose, comparison, parameters, and return type. No redundant or filler language is present.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the tool's purpose, usage context relative to siblings, all parameters, and return value shape. The existence of an output schema reduces need for describing return structure further. Minor gaps like potential errors or rate limits are not addressed, but for a read-only search tool this seems adequate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Although the JSON schema provides no descriptions (0% coverage), the tool description compensates by explaining each parameter: query as natural language, k for result count with default and max, language as optional filter with examples (php, javascript, python, sql). This fully resolves parameter semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with 'Busca código fuente indexado en Hipocampo (RAG)', clearly stating it searches indexed source code. It further distinguishes from sibling search_hipocampo by specifying it filters code_snippet memories and returns code fragments with file location, making the tool's purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly compares to search_hipocampo ('Similar a search_hipocampo pero...'), indicating this tool is for code-specific searches while the sibling handles broader memory types. It provides context on filtering behavior but does not offer explicit 'when not to use' scenarios, so it earns a 4 rather than 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Since no annotations are provided, the description fully carries the behavioral disclosure: read-only, no side effects, no rate limits, hybrid search over technical and profile memory, and explicit return format including no-match behavior. This exceeds typical transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with a clear opening, behavioral notes, alias note, and dedicated Args/Returns sections. Every sentence provides value, and it remains reasonably compact.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's moderate complexity, the description covers purpose, usage, behavior, parameters, and return format. The output schema also exists, but the description still summarizes the return values, making it fully self-contained and contextually complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has 0% description coverage, but the description's Args section fully explains query as natural language text with a 500-character max and examples, and session_id as an optional filter. This adds substantial meaning beyond the schema's bare types.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with 'Busca en el Hipocampo' and elaborates 'Realiza búsqueda semántica + léxica híbrida en las bases de datos de memoria del usuario', clearly identifying the verb, resource, and scope. It also distinguishes this tool from the alias quick_hipocampo_search and other memory tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states the read-only nature and no rate limits, providing a safe-search context. It names the alternative quick_hipocampo_search for quick calls with a short name, and explains the session_id filtering condition, giving clear when-to-use guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the burden of disclosing behavioral traits. It explains the behavioral consequences of each level (e.g., episodica is comprimible, semantica is protected, automatica is never compressed), which adds valuable context beyond the schema. It does not detail error handling or reversibility, but the core behavior is well covered.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured: a one-sentence purpose, a bulleted list of levels with explanations, followed by Args and Returns sections. It is concise with no unnecessary words, and every sentence provides meaningful information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple setter tool, the description is fairly complete: it explains the levels, parameters, and return value. It could be more complete by mentioning handling of invalid IDs or invalid nivel values, but the explicit enumeration of valid nivel values mitigates one of these gaps. Overall, it is adequate for the tool's complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has no property descriptions (0% coverage). The description fully compensates by explaining both parameters: 'id' as the memory ID and 'nivel' as the new level, explicitly listing all valid values. This provides complete semantic meaning for the agent.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose with a specific verb ('Cambia') and resource ('nivel jerárquico de un recuerdo'). It distinguishes itself from sibling tools by focusing specifically on changing hierarchical levels, which is a unique operation compared to siblings like compress_hipocampo or update_hipocampo.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides context by explaining the three levels (episodica, semantica, automatica) and their compression/checkpoint implications, which implies when each level might be appropriate. However, it does not explicitly mention when to use this tool versus alternatives or any exclusion criteria.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description states that the tool deletes a link and returns a confirmation, but with no annotations, the burden is on the description to disclose behavioral traits. It does not mention side effects, whether deletion is permanent, permission requirements, or behavior when the link does not exist.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is structured with a clear one-line purpose, an Args section, and a Returns section. Each sentence is informative and there is no unnecessary filler, though the format could be slightly more compact.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the common invocation modes (by id or by source/target/type) and the return value, but it lacks edge-case behavior such as what happens if both id and source_id are provided, or if neither is provided. It also does not explain how this tool fits within the broader tool set for graph manipulation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Given zero description coverage in the schema, the description effectively explains each parameter's role and the conditional logic (id vs source_id+target_id+relation_type). This adds significant meaning beyond the schema's titles and defaults, though it could clarify whether source_id is required when id is absent.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Elimina un enlace' = deletes a link) and the resource ('grafo de memoria' = memory graph). This distinguishes it from sibling tools like delete_hipocampo, which likely deletes nodes, and link_hipocampo, which creates links.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides conditional parameter guidance (use id if known, otherwise source+target+type) but does not explicitly discuss when to use this tool versus alternatives like delete_hipocampo or other graph operations. There is no mention of prerequisite conditions or contexts where this tool is preferred.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states that the tool deletes a webhook and returns a confirmation, but it does not disclose whether deletion is permanent, whether any related data is affected, or any error behavior. As a destructive operation, this lack of context is a notable gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact, with a single sentence for the main action and short 'Args' and 'Returns' sections. It is front-loaded with the purpose and contains no redundant information. Every element serves a functional role.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with one parameter and a simple delete action, the description covers the essential operation and the parameter's meaning. However, it omits usage context, such as prerequisites or error handling, and does not mention where the ID comes from. Given the lack of annotations and the presence of an output schema, a bit more context would be expected, but the simplicity of the tool mitigates the gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The only parameter, 'id', is explained as 'ID del watch a eliminar' in the description, which adds meaning beyond the bare integer in the schema. However, it does not specify how to obtain this ID (e.g., via list_watches) or any validation rules. The description compensates for the 0% schema coverage but stays minimal.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description begins with 'Elimina un webhook registrado por su ID', which clearly states the action (delete) and the resource (a registered webhook/watch). This distinguishes it from sibling tools like watch_hipocampo and list_watches, which perform create and list operations. The tool name aligns with the description, making the purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It does not mention that the ID can be obtained from list_watches, nor does it contrast with other deletion tools like delete_hipocampo. The usage context is only implied from the tool name and purpose.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the burden and adds meaningful behavioral details: content triggers automatic embedding regeneration, and unprovided fields remain unchanged. It also states the return type as a confirmation. It doesn't cover error cases or permissions, but it discloses the most important side effects for an update operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and well-structured: purpose first, key behavioral notes, then a clear Args list, followed by Returns. Every sentence adds value and there is no redundant filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 5-parameter update tool with an output schema, the description covers all parameters, partial-update semantics, and the embedding regeneration side effect. It doesn't mention failure behavior or authorization requirements, but these are not critical for the core update operation and the output schema likely defines the confirmation structure.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 0% description coverage, but the description compensates by documenting all five parameters with semantic cues: id as numeric, content as optional with embedding regeneration, memory_type with an example, code as a short label, and categories as a new list. This goes well beyond the schema's bare type declarations.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description begins with a specific verb and resource: 'Actualiza un recuerdo existente en el Hipocampo (memoria_vectorial)' — explicitly an update operation on existing memories. This clearly distinguishes it from sibling tools like save_hipocampo (create) or delete_hipocampo.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides context that the tool updates only provided fields ('Los campos no proporcionados no se modifican') and that content triggers embedding regeneration, but it does not explicitly state when to choose this tool over alternatives or provide exclusions. Usage is implied rather than directly contrasted with siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. It discloses three analysis behaviors and states it returns a validation report with recommendations, strongly implying read-only behavior. It does not explicitly confirm non-mutation or permissions, but for a validation/report tool this is sufficient context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and well-organized: a one-line purpose, three numbered checks, and clean Args/Returns sections. Every sentence earns its place, and the structure makes it easy for an agent to parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter validation tool with an output schema, the description is fairly complete: it explains the input, the validation logic, and the output. It lacks explicit usage guidance and caveats, but those are not critical for such a focused tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema only defines rule_id as an integer with 0% description coverage. The description compensates by explaining that rule_id is the ID of the immune rule to validate, adding domain meaning beyond the raw type. More details like format or examples would help, but the single parameter is adequately clarified.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool validates an immune rule (Nivel 4) and provides three specific checks, making the purpose concrete. It distinguishes this tool from siblings like review_automatica by focusing on immune rules and their validation workflow, though it does not explicitly name alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies the tool is for validating 'automatica' rules marked as immune, listing the analysis steps. However, it does not explicitly state when to use this tool over siblings or mention exclusions, leaving the usage guidance somewhat implicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.