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

With no annotations, description covers idempotency (no failure if exists), automatic intermediate directories, and path constraints. Missing return value/response details, but output schema exists.

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 concise sentences, each adding value. First sentence states action, second explains behavior, third states constraint. No fluff.

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?

Tool is simple with one parameter; description covers core behavior. Could mention return format (e.g., success indicator) but not critical for selection/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 already describes path, but description adds critical context: absolute path required and automatic creation of intermediate directories, which is not evident from schema 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?

Description clearly states the tool creates a directory, including all necessary intermediates, and equates it to mkdir -p. It distinguishes from sibling file operations like move_file and write_file.

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?

Describes the mkdir -p equivalence and path constraint (must be within allowed directories). Lacks explicit when not to use or alternatives, but purpose is clear.

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. It discloses error behavior (ValueError if old_string not found) and matching requirements, but does not describe success output, atomicity, or file existence requirements. The output schema exists but is not referenced.

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 three sentences, front-loading the primary action. Every sentence provides useful information; no redundancy or fluff.

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 complexity (4 params, no annotations, output schema exists), the description covers the edit mechanism, matching requirements, and error conditions. It lacks specifics on return value and preconditions (e.g., file must exist), but the output schema likely covers return details. Overall 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?

Schema coverage is 100%, so baseline is 3. The description adds valuable nuance: emphasizing exact matching for whitespace/indentation, uniqueness, and the role of `expected_replacements`. This goes beyond the schema's parameter 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 the tool's action (edit a file by replacing text), specifies the mechanism (exact snippet replacement), and distinguishes it from `write_file` by noting it only sends the changed part. The verb and resource are explicit.

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 indicates this is the preferred editing approach and advises on proper use (matching whitespace, providing context). However, it does not explicitly state when not to use it or mention alternatives like `write_file` for creating new files.

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?

Discloses shell detection, blacklist check, output truncation, combined stderr, and exit code reporting. With no annotations, this covers key behaviors. Lacks details on blacklist rejection behavior (e.g., error vs silent) and timeout handling beyond parameter.

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?

Extremely concise: 7 sentences, each adding unique value. Front-loaded with core purpose, then platform details, security, output handling, and error detection. No fluff.

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 an output schema exists, the description adequately covers input, execution, and output. Could mention synchronous nature and blacklist error handling, but overall sufficient for a moderately complex 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?

Schema coverage is 100%, so description adds marginal value over schema. Briefly mentions shell detection relevant to 'command' parameter, but no additional parameter meaning beyond schema 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 it executes a shell command and returns combined stdout+stderr output. It distinguishes from sibling 'execute_command_streaming' by implying batch output, and from 'start_process' by focusing on output capture. The verb 'execute' and resource 'command' are precise.

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?

Provides basic context like shell detection and security blacklist, but does not explicitly guide when to use this vs streaming or process management siblings. No 'when not to use' or alternatives listed.

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. It discloses that output is collected line by line and returned as a single string, and that the command is blocked if it matches a security blacklist. However, it does not clarify side effects, blocking behavior, or whether the command runs in a sandbox, leaving gaps for an AI agent.

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 three sentences and one additional note. It front-loads the purpose, follows with intended usage, and adds a behavioral constraint. Every sentence is necessary and well-structured 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 presence of an output schema and context signals, the description adequately covers the tool's purpose and key constraints. It could be more explicit about when to use this over sibling tools like 'execute_command', but it provides enough context for most use cases.

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 100%, so the parameter descriptions already explain each parameter. The tool description adds little beyond schema; it merely reinforces what the schema says (e.g., 'Shell command to execute'). Hence, the description meets the baseline but does not provide additional 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 clearly states the tool executes a long-running command with incremental output, distinguishing it from the sibling tool 'execute_command' which presumably returns output all at once. It specifies the resource (command) and the outcome (incremental output).

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 it's intended for commands that produce output over time (builds, tests, long scripts) and mentions that true streaming requires SSE, which provides context. However, it does not explicitly state when not to use it or directly name alternative tools, leaving some ambiguity.

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 discloses that the tool performs an immediate kill without waiting for clean termination, equates to SIGKILL, and cleans the session log after termination. It does not mention potential data loss or open file consequences, but given the nature of SIGKILL, the behavior is sufficiently 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?

The description is very concise with three short sentences and a bullet-like structure. Every sentence adds value: purpose, equivalence, and usage alternative. No 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?

With one parameter and an output schema present (though not shown), the description covers the core behavior and even mentions session cleanup. It lacks explicit return value details, but the output schema likely covers that. The description is complete for a simple kill 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 input schema covers 100% of parameters (only 'pid') with a description. The tool description does not add new parameter semantics beyond what the schema already provides. Baseline 3 is appropriate.

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 kills a process immediately without waiting for clean termination, using verbs like 'Mata' and referencing Unix/Windows signals. It distinguishes itself from the sibling tool 'kill_process' by noting that the latter can perform a cleaner shutdown with force=False.

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 (immediate kill equity to SIGKILL/TerminateProcess) and when to use the alternative (kill_process with force=False for cleaner termination). This provides clear usage 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 provided, so the description must carry the burden. It states it returns configuration but does not disclose side effects, idempotency, or safety. Read-only is implied but not explicit.

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?

One concise sentence with no fluff. Front-loaded and 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?

Given zero parameters and an output schema, the description is adequate. It could mention that the call is safe and repeatable, but overall it covers the essential return value detail.

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?

There are zero parameters, so the description compensates by specifying the output includes 'type metadata', adding value beyond the empty 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 verb 'return' and the resource 'active runtime configuration with type metadata'. It is specific and distinct from sibling tools like 'set_config_value'.

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 on when to use this tool versus alternatives (e.g., set_config_value). Missing context on typical use cases or prerequisites.

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 return types (metadata + preview for text files) but does not mention limitations for binary files, permissions needed, or error handling. With no annotations, more detail would be beneficial.

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, front-loaded with purpose, efficient and clear with 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?

Given the presence of an output schema and the tool's simplicity, the description covers the key aspects: what metadata is returned and the behavior for text files. Minor omission on directory behavior and edge cases, but overall 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?

Schema coverage is 100% and adds meaning by describing the path as absolute. The description repeats this but does not add further detail 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 returns metadata about a file or directory, listing specific metadata fields and a content preview. It distinguishes from sibling tools like read_file and list_directory.

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 description implies use for metadata and preview, but lacks explicit when-not-to-use or alternative suggestions.

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 bears the responsibility for behavioral disclosure. It states that the tool returns column metadata (data type, length, nullable, primary key, comment) and does not indicate any side effects, destructive actions, or authorization needs. While the behavior is clear as a read-only operation, the description does not explicitly state it is non-destructive or safe to call. Given the lack of annotations, a score of 3 is appropriate; it adds some context but not comprehensive 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 consists of two concise sentences. The first sentence states the purpose and the second lists the return fields and provides an SQL equivalence. Every sentence adds value without redundancy or fluff. The structure is front-loaded with the primary action, making it efficient for an agent to parse quickly.

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 the tool has an output schema (present but not shown), low complexity (2 parameters, required one), and no nested objects, the description adequately covers the tool's purpose and return values. It mentions that the tool works on tables (and the input schema says 'tabla o vista'), and specifies that the column comment is returned if it exists. It could be slightly improved by noting the default ordering of columns, but it is sufficiently complete for a simple describe 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 input schema covers both parameters (table_name and schema) with descriptions. The schema description coverage is 100%, so the baseline is 3. The tool description adds minimal extra information beyond the schema: it mentions the return of column comments ('si existe') which is not in the schema, but does not provide parameter syntax or format details. Overall, the description adds modest value over the schema, warranting a score of 3.

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: 'Describe la estructura de una tabla en SAP HANA Cloud.' It specifies the verb (describe) and resource (table structure), and lists what is returned (columns, data type, length, nullable, primary key, column comment). This distinguishes it from sibling tools like hana_list_tables (which lists table names) and hana_execute_query (general querying).

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 mentions 'Equivale a DESC table en SQL*Plus', which implies usage for obtaining table structure, similar to SQL*Plus. However, it does not provide explicit guidance on when to use this tool versus alternatives (e.g., hana_execute_query for similar informtion) or when not to use it. The usage context is implied but lacks exclusions or alternative recommendations.

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 discloses the destructive nature of DROP/TRUNCATE and the confirmation safety measure. However, it does not discuss other behavioral traits such as required permissions, autocommit behavior, or error handling. The warning is good but 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 extremely concise: two sentences and a warning line. It is front-loaded with the main action and uses bullet points for key precautions. Every sentence 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?

The description covers purpose, safety, and parameters. Since there is an output schema (as indicated by context signals), the absence of return value details is acceptable. For a DDL tool, it adequately explains the core behavior, though it could mention post-execution effects like schema changes.

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 100% coverage with descriptions for both parameters. The description reinforces the confirm parameter's purpose but does not add significant new meaning beyond what the schema provides. Baseline is 3, and the description matches that.

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 DDL statements (CREATE, ALTER, DROP, GRANT) in SAP HANA Cloud. It uses a specific verb ('Ejecuta') and defines the resource ('sentencia DDL'). This distinguishes it from sibling tools like hana_execute_query (which executes queries) and hana_describe_table (which describes tables).

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 requires explicit confirm=True to prevent accidental execution and warns about irreversible DROP/TRUNCATE. This provides clear context for safe usage. However, it does not explicitly mention when to use this tool versus alternatives (e.g., hana_execute_query for queries), but the sibling tool names imply 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?

Describes row limit and per-SQL-type behavior. No annotations provided, so description carries burden; lacks details on error handling or read-only nature but sufficient for basic understanding.

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?

Six sentences, well-structured, front-loaded with action, 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?

Covers output expectations for different SQL types and row limit. Lacks error handling or timeout info, but adequate given sibling tools and output schema existence.

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 covers all three params with descriptions. Description adds nuance about row limiting to avoid dumping tables, providing value beyond 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?

Clearly states it executes SQL in SAP HANA Cloud, distinguishes SELECT, DML, and CALL behaviors. Distinct from siblings like hana_describe_table and hana_execute_ddl.

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?

Explains row limit and max_rows usage for controlling output. Does not explicitly contrast with sibling tools or state when not to use, but context is clear.

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 discloses the use of M_TABLE_STATISTICS instead of COUNT(*), which is a key behavioral trait. However, it does not mention potential performance implications, whether counts are approximate, or any required permissions.

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 with two sentences. The first sentence states the purpose, and the second adds behavioral context. No extraneous 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?

Given the simplicity of the tool (2 parameters, output schema exists), the description covers the essential purpose and key behavioral aspect. It could mention limitations of M_TABLE_STATISTICS (e.g., potential staleness), but overall it is 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?

Schema coverage is 100% with clear descriptions of both parameters. The tool description adds no additional parameter-specific information, so it meets the baseline of 3.

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 returns row counts for one or multiple tables. It distinguishes itself from COUNT(*) by mentioning the use of M_TABLE_STATISTICS, setting it apart from general query tools like hana_execute_query.

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 use for monitoring with 'rápido para monitorización' and contrasts with COUNT(*), providing context. However, it does not explicitly state when not to use this tool or list alternatives among siblings, leaving some ambiguity.

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 full responsibility for behavioral disclosure. It merely states the tool returns data without revealing safety, authentication needs, or potential side effects. As a read-only operation, this is minimal 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 extremely concise: two sentences that efficiently convey purpose and use case. No unnecessary words, and key information is front-loaded. 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?

Given the tool has no parameters and an output schema is present (handling return values), the description is complete for basic monitoring. It could optionally mention that data is real-time or cached, but overall it sufficiently covers the tool's interface.

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 the schema coverage is effectively 100%. Per the rubric, 0 parameters yields a baseline of 4. The description does not need to add parameter details as there are none, and it correctly provides no misleading information.

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 returns SAP HANA Cloud system information including memory, CPU, and active alerts. It distinguishes itself from sibling HANA tools like hana_execute_query or hana_list_tables by focusing on system monitoring.

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 a clear usage context: 'Útil para monitorización básica del Free Tier' (useful for basic Free Tier monitoring). While it does not explicitly exclude other scenarios or mention alternatives, the context is clear and sufficient for basic decision-making.

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 bears full responsibility for behavioral disclosure. It does not state that the tool is read-only, safe, or requires specific permissions. As a listing operation, the risk is low, but the description should explicitly confirm non-destructive 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 two concise sentences that immediately convey the tool's purpose and output. No unnecessary words or 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 presence of an output schema, the description adequately covers what the tool returns (name, owner, system schema). It does not mention the filter parameter, but that is documented in the input schema. Slight gap in not emphasizing filtering capability.

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 100%, so the input schema fully documents the filter_name parameter. The tool description adds no further meaning beyond that already in the schema. Baseline 3 is appropriate.

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 lists visible schemas for the current user and specifies the fields shown (name, owner, system schema). It distinguishes from sibling tools like hana_list_tables and hana_describe_table.

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 listing schemas but provides no explicit guidance on when to use this tool over alternatives or any preconditions. The context from sibling tools makes the purpose obvious, but explicit guidelines are absent.

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 disclose behavior. It indicates a read-only operation ('Muestra...') and lists output fields. It does not mention permissions or large schema performance, but the tool is simple and non-destructive.

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 concise sentences that front-load the core action and output details. No unnecessary 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?

For a simple listing tool with an output schema, the description covers what it lists, the schema parameter, and output details. It is complete enough for an agent to use 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?

All parameters are fully described in the input schema (100% coverage). The description adds minor context (e.g., 'TABLE, VIEW, CALC VIEW, o vacío') but does not significantly enhance understanding 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?

Description clearly states it lists tables, views, and Calculation Views of a schema in SAP HANA Cloud, and shows name, type, column count, and comment. This distinguishes it from sibling tools like hana_describe_table (single table) and hana_execute_query (arbitrary queries).

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 listing schema objects but does not explicitly state when not to use or mention alternative tools. However, the purpose is straightforward and context signals clarify it is a read-only listing.

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?

Despite no annotations, the description discloses that the tool never returns passwords or sensitive data, and that it returns server information. It could be more explicit about being read-only and safe to call multiple times, but it covers key behavioral traits.

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 sentences, each adding value: purpose, details of verification, and safety guarantee. Front-loaded with the main action, no redundant or filler 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 simple connection test with no parameters and an existing output schema, the description adequately explains what the tool does and what information it returns (version, user, schema), including a safety guarantee. It is complete enough for an agent to understand its function.

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 schema coverage is 100%. According to guidelines, this earns a baseline of 4. The description does not need to add parameter info, and it does not attempt to mislead.

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 tests the connection to SAP HANA Cloud and returns server information including version, connected user, and current schema. This distinguishes it from sibling HANA tools like hana_execute_query or hana_describe_table, which serve different purposes.

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 verifying connectivity and credentials, but does not explicitly state when to use this tool versus alternatives like hana_get_system_info. No exclusions or when-not-to-use guidance is 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 discloses key behaviors: it writes input to stdin, waits for new output, includes a timeout, and appends a newline automatically. However, it does not explain what happens if no output is produced or if the process terminates.

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 front-loaded purpose sentence, followed by usage context and a clear, multi-step example. Every sentence adds value.

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 the essential workflow and includes practical example steps. It could mention error handling or edge cases, but overall it is sufficiently 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 coverage is 100% (baseline 3), and the description adds value by noting the automatic newline appending and providing defaults for timeout and max_lines, which are not fully explained in 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 verb ('Envía input') and resource ('proceso activo'), and the example flow distinguishes it from siblings like read_process_output and execute_command by emphasizing interactive REPLs.

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 'Ideal para REPLs interactivos' and provides a step-by-step example showing when to use it with start_process and kill_process, but does not explicitly state when not to use it or list alternative 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 fully discloses the signals used (SIGTERM, SIGKILL/TerminateProcess) and the return behavior, leaving no ambiguity about what the tool does.

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 sentences with no waste. The core purpose is front-loaded, and each sentence 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?

The description covers the essential behavior for a process-killing tool, including signal details and return value summary. With an output schema present, it need not detail return values further. Missing prerequisites like permissions are acceptable omissions.

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 100%, so baseline is 3. The description adds 'graceful shutdown' and 'immediately kill' context beyond the schema, but does not provide additional parameter meaning beyond what the schema already specifies.

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 terminates a running process by PID, using a specific verb and resource. It distinguishes from siblings like start_process and list_processes.

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 explains the default SIGTERM and force option for SIGKILL, providing clear usage context for normal vs. immediate termination. However, it does not differentiate from the sibling force_terminate.

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 provided, so description carries burden. It explains output format and sandbox respect, but omits error handling or side effects. Adequate for a simple read 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?

Two concise sentences with no redundancy; front-loaded with key action and output details.

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?

Covers core functionality, output format, and sandbox constraint. Output schema likely provides further details on return values, making this sufficient for the tool's 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?

Schema already describes all parameters fully (100% coverage). Description adds no extra meaning beyond what schema states, so baseline 3 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 clearly states the tool lists directory contents with file sizes and types, distinguishing it from siblings like get_file_info (single file) and search_files (search by pattern).

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 on when to use this tool versus alternatives like search_files or read_file; lacks when-to-use and when-not-to-use 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?

Without annotations, the description is the only source. It mentions cross-platform compatibility and that results are filtered/sorted. However, it doesn't disclose potential system impact, permission requirements, or performance characteristics. Adequate but could be richer.

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 sentences, each adding value: what it lists, cross-platform support, and behavior. Front-loaded with the core purpose. 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 description covers the main functionality and mentions output format (formatted table). With an output schema present, return value details are not required. However, it omits default behavior (lists all processes) and scope (e.g., only user processes or all). Very close to complete for a simple 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?

Input schema already fully describes both parameters (filter_name and sort_by). The description adds no new parameter information beyond 'filtered and sorted as requested'. Baseline 3 is appropriate given 100% schema 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 lists running processes with specific fields (PID, name, CPU%, memory usage). It distinguishes itself from sibling tools like kill_process or start_process by being a read-only listing 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?

No guidance on when to use this tool versus alternatives like kill_process or execute_command. Does not specify when the output might be useful or any prerequisites.

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 key behavioral trait: completed sessions are automatically cleaned up when listed. No annotations exist, so the description carries the full burden. It adds value by noting this side effect, though it could mention if the operation is safe or has rate limits.

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 front-loaded purpose and no unnecessary words. Every sentence provides essential information about the tool's function and side effects.

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 core purpose, displayed fields, and cleanup behavior. It is complete enough, though additional details about ordering or limits are not necessary given the 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 (schema coverage 100%), so baseline is 4. The description adds meaning by explaining what is displayed and the cleanup behavior, which enriches the empty 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 it lists active process sessions ('Lista todas las sesiones de proceso activas') and shows specific fields (PID, command, status, etc.). It implicitly distinguishes from sibling tools like list_processes by focusing on 'sessions' from start_process.

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?

While the description mentions sessions from start_process, it does not explicitly state when to use this tool versus alternatives like list_processes or read_process_output. Usage context is implied but not directly 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?

No annotations provided, so description carries the burden. It discloses move vs rename logic and directory constraints. Could mention permissions or error handling, but overall transparent for a file 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?

Three concise sentences, no redundancy, front-loaded with core action. Every sentence adds essential behavior 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?

Simple tool with high schema coverage and output schema present. Description covers main behavior and constraints. Could mention return value or error conditions, but sufficient for typical usage.

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 has 100% coverage, but description adds value by specifying absolute paths and explaining how destination existence affects behavior, which is not in the schema 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 it moves or renames a file or directory, specifying behavior based on destination existence. This distinguishes it from sibling tools like read_file or write_file.

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 explains it works within allowed directories and provides clear behavioral rules. However, it does not explicitly mention when not to use or alternatives, though no sibling duplicates this function.

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 exist, so the description carries the transparency burden. It mentions security sandbox enforcement and error types, but does not disclose idempotency, rate limits, or other traits.

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?

Four front-loaded sentences, each serving a distinct purpose: purpose, pagination use case, security, and errors. 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?

Covers purpose, pagination, security, and errors. Lacks explicit mention of file encoding or that it only handles text files, but given the output schema exists, it is sufficiently 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?

Input schema has 100% coverage, so baseline is 3. The description reinforces the pagination purpose for offset and length, but adds minimal new 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 'Read a text file and return its contents' with a specific verb and resource. The name 'read_file' and mention of pagination distinguish it from siblings like 'read_multiple_files' and 'get_file_info'.

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 large files via pagination but does not explicitly state when to use this tool versus alternatives or provide any 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 provided, so description carries full burden. It mentions output format (content separated by clear headers) but omits behavioral details like truncation at max_lines_each, permissions, or encoding. The schema partially covers max_lines_each, but the description should restate this.

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 three sentences. It front-loads the main action, then provides use case and output behavior. No redundant 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?

Given the presence of an output schema and complete input schema, the description adds value by specifying the output format. It is almost complete but lacks mention of error conditions or file type restrictions beyond 'text files'.

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 100% with both parameters described. The description does not add extra meaning beyond the schema (e.g., format of paths, or implications of max_lines_each). Baseline of 3 is appropriate.

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 verb 'Lee' (reads) and the resource 'varios ficheros de texto' (multiple text files). It distinguishes itself from sibling 'read_file' by emphasizing multiple files in a single call.

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 usage context: 'Útil para comparar ficheros o cargar múltiples módulos de una vez.' It suggests when to use but does not explicitly mention when not to use or list alternatives like 'read_file'.

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 waiting behavior, status return, and incremental reading. However, it doesn't clarify whether output is consumed upon reading or if there are side effects, which is a minor 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 brief and well-structured: first sentence states purpose, second explains behavior, third gives usage advice. No unnecessary 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?

For a simple read tool with no annotations but an output schema, the description covers behavior, return values, and usage pattern. It is complete enough for the agent to use 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 100% with parameter descriptions. The tool description reinforces timeout_seconds but adds no new meaning beyond the schema, so baseline score 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 clearly states the tool reads accumulated output of an active process. It uses a specific verb ('Lee') and resource, and distinguishes itself from siblings like start_process, kill_process, and interact_with_process.

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 advises calling the tool repeatedly for incremental output and explains behavior when process finishes. While it doesn't explicitly mention when not to use it, the context is clear compared 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?

The description adds valuable behavioral context: it specifies that content_search only scans text files (skips binary), and returns matching absolute paths with optional match context. Since no annotations are provided, this description carries the full burden and does so well, although it could mention that the tool is read-only and non-destructive.

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 (5 lines) with bullet points. It is front-loaded with the core purpose, then details in a structured list. Every sentence serves a clear purpose, no fluff.

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 existence of an output schema (details of return values), the description provides adequate context: it mentions both name and content search, parameter roles, and the result format. It could benefit from a brief note on performance or limits beyond max_results, but overall it is complete for a search 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 input schema covers all 5 parameters with descriptions (100% coverage). The tool description adds some nuance (e.g., 'pattern' uses glob or substring, content_search is text-only) but mostly repeats schema information. The clarification about binary skipping in content_search adds marginal value, keeping this at baseline 3.

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 'Search for files by name pattern and/or content substring' which is a specific verb+resource+scope. It clearly separates two search modes (name pattern and content substring) and mentions the return format (absolute paths with optional context). This distinguishes it from siblings like list_directory (simple listing) and read_file (reading full content).

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?

While the description effectively explains what the tool does, it does not provide explicit guidance on when to use this tool over alternatives. It implies usage for file searching but does not mention exclusions (e.g., when to use other tools like execute_command with grep) or context-specific recommendations.

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 present, so the description must carry full behavioral disclosure. It indicates that updating is a mutating operation and that changes are persisted to YAML. However, it omits details such as whether the config must already exist, side effects on running processes, or error conditions. The description is adequate but not comprehensive.

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 sentence that front-loads the verb and resource, with no redundant words. Every part 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 two-parameter tool with an output schema, the description covers the primary action. It lacks context about the config location, persistence guarantee, and return value, but these are partially addressed by the schema and output schema. Additional details would improve completeness.

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 100% with descriptions for both parameters. The description adds no additional meaning beyond what the schema provides for the 'key' and 'value' fields. It does not explain the dot-separated format or validation rules further.

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 specifies the verb 'Update', the resource 'runtime config value', and the outcome 'persist it to YAML'. It distinguishes itself from sibling tools like 'get_config' (reading) and file operations, 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 implies usage context (runtime config), but does not explicitly state when to use this tool versus alternatives like 'write_file' or how to structure the key. No guidance on prerequisites or exclusions is 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?

No annotations provided, so description carries full burden. It explains that the process stays alive, stdout/stderr are captured, and it returns PID and initial output. Could mention termination or resource implications, but sufficient.

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 sentences, front-loaded with purpose, no fluff. Every sentence adds value and is 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?

Given moderate complexity and presence of output schema, description covers purpose, usage, behavior, and references sibling tools. Minor gap: doesn't explicitly mention that it's for long-running processes, but still 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?

Schema coverage is 100%, so baseline 3. The description does not add meaning beyond the schema; it merely restates the command parameter as 'Comando a ejecutar'.

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 starts a background process and returns its PID. It distinguishes from 'execute_command' by emphasizing that the process remains alive and output is buffered.

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 contrasts with 'execute_command' and advises using 'read_process_output' and 'interact_with_process' for REPLs, providing 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?

No annotations provided; description carries full burden. Discloses automatic parent directory creation, extension validation, and return format. Lacks details on side effects like encoding or size limits, but adequate for a basic file write 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?

Three focused sentences: purpose, constraints, output. No redundant information, 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?

Given the presence of an output schema and the tool's simplicity, the description covers all essential aspects: purpose, constraints, and return value. No gaps for a file write operation.

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 covers all parameters with descriptions. Description adds value beyond schema by mentioning automatic directory creation, which is not in 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?

Clearly states the verb (write/append) and resource (file), distinguishes from siblings like read_file and move_file. Includes specific constraints about directory creation and extension blocking.

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?

Provides constraints (allowed directory, blocked extensions) but lacks explicit guidance on when to use this tool versus alternatives like edit_file_diff for partial edits or create_directory for directory creation.

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