list_agent_evaluations

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

With no annotations, the description carries the full burden and largely meets it: it discloses the row shape (evaluation_name, latest_run_status/progress/summary, score_trend of last 5), the pagination model ('Page-numbered') and a hard limit ('page_size is capped at 100'). It does not state permission/auth requirements or whether an out-of-range page errors or returns empty, which keeps it out of the top band.

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?

Front-loaded with the purpose sentence, then filters, then return shape, then the alternative-tool routing. Every sentence either adds a filter contract, a return contract, or a routing rule; nothing is padding.

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?

No output schema and no annotations, so the description has to supply the return contract and constraints, and it does (row fields, trend window, page cap). The only material omission for a 6-param tool is the semantics of 'order', plus the absence of any default/range hint for page_size beyond the cap.

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 0%, so the description must compensate, and it does for five of six params: search is defined as substring match on name, agent_id/evaluation_id as filters, page/page_size as page-numbered with a 100 cap. The 'order' parameter is never explained (no direction, no sort field, no accepted values), leaving one blind spot.

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?

States a specific verb+resource ('List agent<->evaluation assignments') plus the payload attribute ('with their latest-run status'), so the agent knows exactly what comes back. It further distinguishes itself from siblings by naming get_agent_evaluation (full detail) and get_agent_evaluation_summary (rollup), which no other tool in the list provides.

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?

Explicitly routes the agent: 'Use get_agent_evaluation for full detail, get_agent_evaluation_summary for the OWASP-coverage/health rollup across all of one agent's evaluations.' The list-vs-detail condition is stated, not inferred, and the filter vocabulary (agent_id, evaluation_id, search) tells the agent when this tool is the right entry point.

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