Ask Peers

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

Annotations (readOnlyHint=false, destructiveHint=false) indicate mutation without destruction. The description adds the runtime/stub distinction, which is useful. However, it does not detail side effects, authentication needs, or what happens to the review data. With annotations providing a baseline, the description adds moderate value.

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 sentences, with the primary action front-loaded. Both sentences are relevant and concise. However, the second sentence about stubs could be integrated more succinctly. Overall, it earns its place without excessive verbiage.

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 (9 parameters, nested objects like reasoning_effort_overrides), the description is minimal. It does not cover what constitutes a 'review round,' return format, error handling, or how peers are selected. There is no output schema, so description should fill gaps but doesn't.

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 only 22%, and the description contains no parameter-level information. The inline description of review_focus in the schema is not repeated in the tool description. With low coverage, the description should compensate but fails to do so, leaving most parameters (9 total, 2 required) unexplained.

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

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

The description clearly states the tool's purpose: 'Run a real API review round against selected peers.' It specifies the verb (Run), resource (API review round), and target (selected peers). This distinguishes it from siblings like probe_peers or session_start_round.

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 runtime behavior ('Runtime default uses real provider APIs; stubs run only when CROSS_REVIEW_STUB=1'), providing some guidance on when to expect real vs. stub execution. However, it lacks explicit instructions on when to use this tool versus alternatives like probe_peers or session_start_round.

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