glm_review

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

With no annotations provided, the description carries the burden of behavioral disclosure. It does state that it returns 'Code review with findings and suggestions' and names the GLM agent, but it doesn't disclose whether code is sent externally, whether the operation is read-only, or any other side effects. Basic transparency is present 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 structured with sections for purpose, use cases, arguments, and return value. It's compact and every line adds information, though the opening 'Code review by GLM agent' is somewhat redundant with the tool name.

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, usage, parameters, and return value, and the presence of an output schema fills any gap about return structure. However, it doesn't mention operational caveats like network requirements or whether files are modified, which would be useful for a review tool operating alongside mutation tools like glm_refactor.

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

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

Schema coverage is 0%, so the description compensates well by explaining each parameter's meaning and enumerating allowed values for review_focus and model (e.g., 'security', 'performance', 'style'; 'haiku', 'sonnet'). This goes beyond the bare schema and helps the agent select appropriate inputs.

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 performs code review via a GLM agent, and specifies use cases (security review, performance analysis, best practices). This distinguishes it from sibling tools like glm_ask or glm_implement.

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

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

It provides explicit 'Use for' guidance, listing the types of review it supports, which gives clear context for when to invoke it. However, it doesn't mention alternatives or explicitly state when not to use it, so it falls short of fully differentiating from similar tools like glm_analyze.

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