summarize_evidence

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the operation's safety and repeatability. The description adds that the result is rendered as a Markdown view, which is a useful behavioral detail. However, it doesn't explain what constitutes 'bounded canonical' or how the request affects output, so it adds only modest context beyond annotations. No contradiction exists.

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 a single sentence with no filler or repetition. It conveys the core output (a Markdown proof summary) efficiently. However, its brevity comes at the cost of essential detail, so while the structure is clean, the content is under-specified for a tool with such a complex input 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?

The request object has many fields and enums (e.g., output_excerpts, sensitive_context, candidate_run_id) that are entirely unexplained. The output schema exists, so return format is covered, but the description provides no guidance on how to construct a valid request or what 'bounded' and 'canonical' mean in practice. An agent would need to infer or search for examples, which is inadequate for a tool of this complexity.

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% — the schema provides only titles, types, and enums, with no field explanations. The description does not mention any parameters or how to populate the required 'request' object, which contains many sub-fields (run_ids, finding_ids, analysis_ids, baseline_run_id, sensitive_context, etc.). With zero compensation, the agent has no guidance on what values to supply, making this dimension critically deficient.

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 states a clear verb ('Render') and a resource ('one bounded canonical proof summary'), and adds that it produces a Markdown view. This is specific enough to convey the core action. However, it doesn't differentiate from related siblings like 'get_evidence' or 'record_finding', so an agent cannot confidently choose this tool over alternatives without deeper investigation.

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 gives no guidance on when to use this tool versus alternatives. It doesn't mention required prerequisites, available data, or cases where another tool (e.g., 'get_evidence', 'get_finding') would be more appropriate. Agents are left to infer from the name alone, which is insufficient in a large sibling set.

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