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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the description is freed to add runtime behavior: newest-first ordering, a 50-per-page cap, and the `nextCursor` follow-up mechanism. It also discloses what is NOT returned inline (brand mentions, citations). No contradictions with annotations.

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 primary action and ordering, then pagination, then filters, then the cross-reference caveat. Every sentence carries distinct information with no redundancy.

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?

For a read-only list tool with no output schema, the description covers ordering, page size, pagination continuation, filter options, include semantics, and cross-resource redirection. It is nearly complete, though it could note whether responses include citation/brand-mention ids to link back to the separate endpoints.

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 100%, so the baseline is 3, but the description adds meaning beyond it: it clarifies that `prompt_id` and `source_url_id` are filters, and that `include` loads parent chains (prompt, monitor, project, organization). That parent-chain explanation enriches the include parameter beyond the schema's enum-style list.

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 and resource ("List the AI responses collected for a project") plus the default ordering (newest first), which distinguishes it from the singular get-response-tool. It also explicitly separates itself from list-brand-mentions-tool and list-citations-tool by noting those resources are not embedded.

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?

Gives clear conditional guidance: pass `prompt_id` for a single prompt's responses, `source_url_id` for responses citing a URL, and query the brand-mentions/citations endpoints for those related resources. No explicit "when not to use" or pointer to get-response-tool for single fetches, so it falls short of a 5.

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