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

With no annotations, the description carries the behavioral disclosure burden. It usefully discloses upsert/dedup behavior and the key limitation 'Does not embed file bytes.' However, it does not clarify whether an update overwrites existing fields, what happens to omitted fields, or any auth/concurrency considerations, so disclosure is only partial.

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?

Three focused sentences with no filler. The primary action is front-loaded, and each sentence adds a distinct piece of information: upsert semantics, text-only scope with alternatives, and the file-bytes limitation.

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 12 parameters, 0% schema description coverage, and no annotations, so the description needs to do substantial work. It gives a solid high-level orientation but leaves most input-field semantics and required-value expectations unexplained. The presence of an output schema does not compensate for the input-side 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?

Schema description coverage is 0%, so the description must compensate. It adds meaning for 'title + project' as the dedup key and restricts content to L0/L1/L2 text fields, but it does not explain required fields like solution_doc or most optional parameters. Referencing the same contract as POST is useful, but not self-contained.

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 names a specific action ('Create or update an archive'), identifies the resource, and gives the dedup key ('title + project'). It also distinguishes itself from sibling tools by being explicitly archive-focused and by referencing the POST /api/v1/archives contract.

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 states when to use this tool ('L0/L1/L2 text fields only') and gives direct alternatives for large files via the attachments upload endpoint or CLI after archive_id is available. This is 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 implies a read-only operation ('get') but doesn't explicitly state that it has no side effects or what it returns. The description doesn't mention any prerequisites, rate limits, or consequences of calling without parameters. This is adequate for a simple retrieval tool 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 concise: two sentences with the purpose first, then specific usage conditions. No wasted words. It's well-structured and front-loaded with the core function, though it could add a brief note on parameters without becoming verbose.

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 an output schema but the description doesn't hint at what is returned, nor how the optional parameters affect the response. Given it's a context retrieval tool with three optional inputs, the description should at least suggest how they scope the query. The when-to-use guidance is strong, but the missing parameter semantics and return behavior leave 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?

Schema description coverage is 0% and the description does not explain any of the three parameters (project, file_paths, task_description). Since all are optional, the agent has no idea how they influence the returned knowledge. The description must compensate for the schema's lack of info but fails to do so.

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 clear purpose: 'Get your profile and relevant team knowledge for current work.' It uses a specific verb ('get') and resource ('profile and relevant team knowledge'). It doesn't explicitly differentiate from memory_recall, but the 'for current work' qualifier suggests context retrieval, distinguishing it from generic recall. Slight ambiguity remains about its exact overlap with siblings.

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 conditions: starting a new task, switching codebase areas, or wanting team conventions. It doesn't mention when not to use or alternatives, but the conditions are clear and actionable. This is sufficient for an agent to decide when to invoke it.

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 disclosure burden. It does disclose the operation's precondition and the fact that it promotes a draft, which implies a state change. However, it does not mention side effects, reversibility, permission requirements, or behavior when the preconditions are not met, so transparency is only partial.

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 sentence that front-loads the key restriction ('Pipeline-only') and communicates the operation plus the exact preconditions. There is no redundant or filler content; every phrase 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?

The description covers selection and preconditions well, and the presence of an output schema reduces the need to describe return values. However, it omits guidance on the optional 'refined_content' parameter, which is important for an agent to know whether to supply it and what format is expected. Thus the definition is adequate but not 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%, so the description must compensate. It only vaguely implies that 'draft_id' identifies the draft being promoted, and it gives no meaning or guidance for 'refined_content'. The description does not add enough value beyond the raw schema to help an agent understand 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 uses a specific verb-resource pair, 'promote a draft to published', and adds the exact scope conditions 'source='pipeline'' and 'exp_status='draft''. This makes it clearly distinguishable from sibling tools like memory_draft_save and memory_submit_response, since it names the precise state transition and pipeline restriction.

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 states when the tool can be used: only for pipeline-sourced experiences that are currently drafts. It does not explicitly name alternative tools for non-pipeline or non-draft cases, so it falls just short of full routing guidance, but the conditionality is clear enough for an agent to decide appropriateness.

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 reveals two key constraints: source is always 'pipeline' and exp_status is always 'draft', which are important for understanding the tool's behavior. However, it omits other behavioral aspects like side effects, return format, or whether this is a write operation (implied by 'save'). The transparency is partial.

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 extremely concise – two short sentences with no filler. It front-loads the critical usage restriction ('Pipeline-only') and then states the purpose. Every word earns its place; there is 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 6 parameters, 0% schema coverage, and no annotations, the description is far from complete. It lacks any guidance on parameter semantics, expected input formats, return values, or error conditions. The output schema exists but isn't visible in the description. For a tool with this complexity, the description is insufficient for an agent to call it correctly without external knowledge.

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 provides no information about any of the 6 parameters (title, content, tags, project, group_key, conversation_id). It does not explain what content or title mean, how tags or project should be formatted, or any defaults beyond what the schema already shows. The description adds zero value 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 states a clear action: 'save a draft memory' – a specific verb and resource. It also distinguishes this from siblings by noting it is pipeline-only and that source and exp_status are fixed. This differentiates it from memory_save and memory_draft_publish, though it doesn't name alternatives explicitly.

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 opening phrase 'Pipeline-only' explicitly restricts usage to pipeline contexts, telling an agent when NOT to use this tool. It implies the agent should prefer memory_save for general saves, but it doesn't name that sibling or state when to use the alternative. Still, the pipeline-only constraint is a clear usage boundary.

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 does not state that this is a write operation (storing feedback), whether it is idempotent, whether prior feedback is overwritten, or any side effects. It only describes the action and when to call it. For a tool that persists data, this is a significant 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 two sentences with zero filler. The first sentence states the action and scale, and the second provides the invocation condition. It is appropriately sized, front-loaded, and every word 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 feedback tool, the description is adequate for basic usage. It covers the purpose and when to call, and the output schema exists so return values need not be described. However, it leaves out the meaning of 'experience_id' and the fact that this is a mutating operation. An agent might call it without fully understanding the required identifier or the persistence implications, making it minimally 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%, so the description must compensate. It adds meaning to 'rating' by defining the 1-5 scale and its endpoints. However, it does not explain 'experience_id' (that it likely refers to a memory_recall result ID) or 'comment' (its free-text nature). With three parameters and zero schema descriptions, the description only partially covers the 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 states a specific verb ('Rate'), a resource ('knowledge result'), and the rating scale (1-5 with meaning). It also ties the tool to memory_recall, distinguishing it from siblings like memory_save or memory_recall itself. An agent can immediately understand what this tool does and how it fits.

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 a clear trigger condition: 'Call this when a memory_recall result helped you solve a problem.' This tells the agent when to invoke the tool. It does not explicitly state when not to use it, but the positive trigger is strong enough for typical scenarios. No alternative tools are named, but the condition implies the context.

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 clearly indicates a retrieval/load operation with no destructive side effects implied, and adds context about the L2 level and what data is included. It does not explicitly discuss failure modes or permissions, but for a get-style tool the load semantics are reasonably transparent.

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, front-loaded sentence states the operation and resource, then lists contents in a compact series and ends with the usage trigger. There is no filler or redundancy; every clause contributes to correct invocation or selection.

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?

Output schema exists, so return values need not be described in the description. The description provides the trigger condition and payload contents, which is enough for most calls, though the optional project parameter and edge-case behavior are omitted. For a low-complexity two-parameter getter, this is nearly 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%, so the description must compensate. It gives meaning to the required parameter via 'by id' and implies archive_id originates from a memory_recall result, but the optional 'project' parameter is never mentioned. This partial coverage is helpful but leaves one parameter semantically unexplained.

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 a specific verb ('Load') and resource ('full archive body (L2) by id'), and enumerates the contents returned: solution_doc, overview, conversation_summary, attachments, document_tree_nodes. It differentiates itself from memory_recall by tying its use to 'type=archive', so an agent can distinguish the tools without opening the schema.

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 says 'Use when memory_recall returned type=archive', giving a concrete trigger condition and naming the sibling (memory_recall) as the relevant alternative. This is clear guidance for selecting this tool over related memory 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?

With no annotations, the description carries the full burden. It discloses that results may include archive previews only when include_archives=True, and that full text comes from memory_get_archive. It doesn't explicitly say whether the operation is read-only, but the search context implies no side effects. Overall, it provides useful behavioral context beyond a bare function call.

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 efficient, packing the core purpose, usage triggers, parameter guidance, and cross-tool referral into three sentences. Information is front-loaded (the 'BEFORE' list), and every clause adds value 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?

Despite having an output schema, the description does not detail the output beyond mentioning archive previews. With 11 optional parameters and only about half explained, the description leaves room for ambiguity on filtering (tags, language, framework) and result count (max_results). An agent may need to consult defaults or infer behavior.

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 explain parameters. It covers 'problem', 'query', 'file_path', and 'include_archives' with usage cues, but leaves 'tags', 'project', 'adaptive', 'language', 'framework', 'max_results', and 'include_user_profile' unexplained. This is partial compensation; the agent must infer meaning for the rest from parameter names alone.

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: 'Search team knowledge base before solving problems.' It specifies the resource (knowledge base) and the action (search), and distinguishes it from siblings by explaining that it returns archive previews only and directs users to memory_get_archive for full text. This preempts confusion with 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?

The description gives explicit 'BEFORE' scenarios (debugging, implementing unfamiliar code, design decisions, etc.) and parameter guidance: 'problem' for focused solutions, 'query' for exploratory search, 'file_path' for context. It also tells when to use memory_get_archive for full text, clearly routing the agent between 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 carry the full burden of behavioral disclosure. It explains what to save and when, but never describes side effects, persistence, deduplication, idempotency, overwrite behavior, permissions, or consequences. The only behavioral hint is the verb 'save,' which does not disclose enough for an annotation-free 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 dense and efficiently structured: a short purpose clause, then scenario-based guidance with clear title/problem/solution patterns, and a final explicit exclusion. Every clause earns its place and the most important information is 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?

Output schema exists, so return-value explanation is not needed. The description provides rich contextual triggers and scope guidance, which is substantial for a tool with 9 optional parameters and no annotations. Yet the unexplained parameters and missing behavioral traits leave some gaps that an agent must infer, preventing a perfect score.

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 does heavily for title, problem, solution, and scope, mapping them to each scenario (e.g., 'title=error summary, problem=what failed, solution=what fixed it'). However, it leaves half the parameters (tags, content, project, group_key, experience_type) unexplained, so compensation is strong but incomplete.

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 ('Save valuable knowledge') and resource, then elaborates through four concrete save scenarios, making the purpose unmistakable. However, it does not name or distinguish sibling tools like memory_archive_upsert or memory_draft_save, so it falls short of full 5-level 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 explicit 'Call this when you:' triggers for four distinct situations (unexpected error, alternative selection, user correction, access info) and gives an explicit exclusion: 'For session archiving, use the /archive skill (not this tool).' This is exemplary 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 behavioral burden. It discloses the evaluation purpose and dependency on memory_recall, but does not state side effects, whether it stores/overwrites data, permissions, or error conditions. Adequate but shallow.

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?

Two sentences with minimal fluff. The timing is repeated ('after using memory_recall results' appears twice), so there is slight redundancy, but each sentence adds distinct value: action and purpose.

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 two required and two optional parameters, the description does not explain how to populate query or result_ids, nor the role of project. Output schema exists, so return values are covered, but the input contract is 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%, so the description must compensate. It hints at 'response text' (response) and 'memory_recall results' (likely result_ids) but does not explain query or project, leaving required and optional parameters ambiguous.

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, resource, and context: submit response text after using memory_recall results. It names the exact prior tool and the evaluation purpose, clearly distinguishing it from siblings like memory_recall or memory_save.

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 'Call this AFTER you've used memory_recall results to answer a question,' giving a clear temporal trigger. It does not mention when not to use or alternatives, but the workflow context is unambiguous.

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