get_rejection_feedback_summary

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

With no annotations, the description carries the burden. It explicitly states 'Read-only view' and explains that deferral/prospect creation happen elsewhere, which is transparent about side effects. It could mention pagination or performance, but for an aggregation summary, this is adequate.

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 long, focuses only on key details, and is front-loaded with the core action. Every word adds value—no fluff.

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?

Although there is no output schema, the description lists the return fields (primaryReasonDistribution, tactical fields, pmf field). This covers the main expected result. It does not explain edge cases like empty results, but the read-only nature and field details are sufficient for a summary tool.

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%, so all parameters are documented in the schema. The description does not add extra meaning beyond what schema already explains, but it does mention the output fields, which are not parameters. Baseline 3 is appropriate.

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 action: 'Aggregate rejection_feedback for a project' and lists the specific output fields. This is specific and distinguishes from siblings, though no sibling does the same thing. It's a clear verb+resource+scope.

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 sets context by noting it's a read-only view and clarifies that side effects occurred at record_response time, not on read. This guides usage for reading aggregated feedback. However, it doesn't explicitly mention when to prefer this over alternatives, though no similar tool exists.

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