meeba-brain

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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the agent knows this is a safe read operation. The description adds the behavioral scope ('Every function/method the given function calls') and frames callees as dependencies. However, it does not disclose whether the result includes only direct calls or transitive dependencies, nor any details about ordering or result structure. This is acceptable given the annotations but not fully 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?

Two concise sentences: the first defines the tool's function and resource, the second provides a reason to use it. No fluff, no repetition of schema or annotation data. The key information is front-loaded in the first sentence.

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

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

The tool is simple (1 parameter) and has an output schema, so return values are already documented elsewhere. The description covers purpose and usage. The only notable omission is whether callees are direct calls only or transitive dependencies, which could influence agent expectations. But overall, the description is sufficiently complete for a read-only lookup tool with annotations and an output schema.

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% for the single parameter function_name, with a clear example ('sync_repository'). The description does not add parameter-specific information beyond the schema, which is appropriate given the high coverage. Baseline 3 applies because the schema carries the meaning.

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 ('get') and resource ('callees') and immediately clarifies what it returns: every function/method the given function calls. It distinguishes from sibling tool get_callers by explicitly noting the direction ('calls' vs 'called by') and adds conceptual meaning ('what it depends on to do its job'). The usage hint about not assuming behavior from the name further clarifies the purpose.

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 clear context: 'Use this to understand a function's behavior by seeing what it delegates to, before assuming what it does from its name alone.' This tells the agent when to invoke this tool (when behavior is unclear from the name). It does not explicitly name alternatives or state when not to use it, but the guidance is direct and actionable.

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?

Annotations already indicate read-only and idempotent behavior. The description adds important context about the data source (parsed call graph) and the guarantee of completeness, which goes beyond the annotations. The parameter description also discloses grouping behavior for name collisions, adding transparency about result organization.

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 no wasted words. The first sentence states purpose and key guarantee; the second frames usage context. Front-loaded and easy to parse.

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

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

For a read-only query tool with an output schema, the description sufficiently covers what it returns (complete call list), when to use it, and its accuracy guarantee. It doesn't describe return formatting, but that's handled by the output schema. Slight additional context about error cases could be added, but overall very 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 100%, and the function_name parameter description is detailed (bare name example, grouping logic). The tool description itself doesn't add parameter-level details, so the baseline of 3 applies per the rubric.

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 every place that calls a given function/method, derived from the parsed call graph. It distinguishes itself from siblings by emphasizing completeness ('not a best-effort guess') and by focusing on callers rather than callees, dependencies, definitions, or text search.

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?

Explicit guidance is provided: use before renaming/changing a function's signature or to understand blast radius before modifying. This clearly indicates when the tool is appropriate, and the contrast with siblings (e.g., get_callees) implies when it is not needed.

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?

Annotations already declare readOnlyHint=true and idempotentHint=true, so the safety profile is covered. The description adds the behavioral context of returning file dependencies but does not disclose any edge cases, performance characteristics, or limitations. Since annotations handle the main safety traits, this is adequate but not rich.

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, front-loaded with the core purpose and immediately followed by practical usage guidance. Every word earns its place, with no repetition of schema or annotations.

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

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

The tool is simple (1 parameter), has an output schema, and is covered by read-only/idempotent annotations. The description provides the intended use case and the schema fully documents the parameter. Together, this gives a complete picture for an agent to select and invoke the tool correctly.

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

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

The input schema covers 100% of the parameter semantics, including a detailed description of file_path with resolution rules (exact match first, suffix fallback). The tool description itself adds no additional parameter detail beyond calling it a 'specific file,' which is redundant with the schema. Baseline 3 applies because the schema does the heavy lifting.

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 and resource: 'What a specific file imports/depends on.' It clearly distinguishes from siblings like get_callees/get_callers by focusing on file-level dependencies rather than function-level relationships. The context ('understand a file's place in the codebase') further clarifies intent.

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

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

The description provides explicit guidance on when to use this tool: 'to understand a file's place in the codebase before assuming what's available to it, or before moving/refactoring it.' It does not explicitly mention alternatives or exclusions, but the usage context is clear and actionable.

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?

Annotations already declare readOnlyHint=true and idempotentHint=true, so the safety profile is known. The description adds value by disclosing the return content (exact file, line range, signature-relevant metadata like async, decorators, docstring) and the ambiguity handling (bare name vs. qualified method name). No contradictions with annotations.

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 exactly two sentences, front-loaded with the core purpose and output, followed by a useful usage tip. Every sentence earns its place with no redundancy or extraneous 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?

This is a simple read-only lookup tool with a single well-documented parameter and an output schema (as indicated by context). The description covers what it does, what it returns, and when to use it. The behavior is fully contextualized for the agent without unnecessary 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?

The input schema description for 'name' fully explains the bare symbol and qualified method name formats, covering 100% of the parameter semantics. The tool description does not add additional parameter details beyond this, so the baseline of 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's purpose with a specific verb ('Finds') and resource ('where a function, class, or method is actually defined') and specifies the exact output type (file, line range, metadata). It differentiates from siblings like search_code (which finds occurrences) and get_callers/callees (which find relationships) by focusing on the definition site.

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 usage context: 'Use this before assuming a symbol's location/signature from memory or from a similarly-named symbol in a different file.' This gives clear when-to-use guidance, though it does not explicitly name alternative tools or state when not to use it. Since sibling tools are reasonably self-evident, this is clear context without 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?

Annotations already declare readOnlyHint and idempotentHint, so the description only needs to add context beyond those. The description adds the 'hybrid semantic + keyword' nature and 'actual indexed content' scope, which is useful behavioral context. It doesn't contradict annotations, but doesn't mention pagination or result limits beyond the top_k schema.

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

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

Two sentences, zero waste. The first sentence states the core function and scope; the second gives usage examples and explicit alternatives. 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?

With an output schema present, return values need no explanation. The description covers the tool's purpose, when to use it, distinguishes from siblings, and the annotations cover safety. For a 2-parameter tool with full schema coverage, the description is complete and provides all necessary context for selection and invocation.

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

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

Schema coverage is 100% for both parameters (query and top_k), so the schema already documents their semantics. The description reinforces the query parameter with 'open-ended questions' but adds no additional meaning for top_k beyond the default and max. Baseline 3 is appropriate when the schema carries the parameter documentation.

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

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

The description clearly states a specific verb (search) and resource (the connected repository's actual indexed content). It explicitly distinguishes from siblings by noting that get_symbol_definition and get_dependencies are more precise for exact symbol/file names, preventing misuse.

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 gives explicit when-to-use guidance: open-ended questions where you don't know the exact symbol or file name. It also names alternatives (get_symbol_definition or get_dependencies) for exact lookups, which is exactly the kind of exclusions/alternatives that deserve full credit.

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