glm_analyze

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

No annotations are present, so the description is the sole source of behavioral information. It explicitly declares READ-ONLY access and enumerates the available capabilities (Read, Glob, Grep, LS, Bash), which clearly communicates the tool's safety profile. It also notes 'Bash (safe commands)' to indicate restricted execution, though the exact safety criteria aren't defined.

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 organized into terse, front-loaded sections: purpose, usage, access, arguments, and returns. Every line adds value, and the structure makes it scannable for an AI agent. The 'Returns' line is brief but acceptable given the presence of an output schema.

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

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

For a read-only analysis tool with three parameters and an output schema, the description covers all key aspects: purpose, use cases, safe access boundaries, and parameter meanings. It lacks explicit examples or exclusions, but the read-only statement and use-case list provide sufficient context for correct invocation.

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

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

The Args section provides human-readable explanations for all three parameters, compensating for the 0% schema description coverage. It clarifies that 'task' is the analysis instruction, 'working_directory' defaults to current, and 'model' accepts 'haiku' or 'sonnet.' This goes beyond the raw schema titles and types.

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

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

The first line 'Analyze codebase using GLM with read access' clearly defines the action and target. The 'Use for' section specifies distinct analysis tasks (code structure, patterns, architecture, dependency mapping) that differentiate it from sibling tools like glm_implement or glm_refactor. The read-only designation further distinguishes it from modification tools.

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

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

The description provides explicit use cases under 'Use for,' outlining when to employ this tool. The read-only access statement implicitly indicates it should not be used for modifications, but it doesn't name specific alternative tools for those cases, which would have pushed it to a 5.

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