search_conversations

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

With no annotations, the description carries the full burden and does disclose meaningful behavior: results are scoped to conversations the caller can access, and the `conversations:read` permission is required. It does not describe the shape of returned records or flag that the two match modes behave differently (exact vs. substring), which would matter for result interpretation.

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 core sentences are tight and front-loaded, but the block opens by restating the tool name as a heading and then appends raw API paths and a 'Tags: Search' line, listing the endpoint twice in two different forms. That transport-level noise does not help an agent select or invoke the tool.

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 two-parameter search tool with no output schema, the definition covers matching semantics, access scoping, permission requirement, and where to go for filters and pagination — enough to call it correctly. Missing is any hint about result volume defaults beyond the schema and what a returned conversation contains.

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 a 3 is the floor, but the description genuinely adds meaning the schema lacks: it explains what `query` is matched against (reference number or contact email) and how each match type behaves. The `limit` parameter is left entirely to the schema, including its silent clamp to 1000.

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 names a specific verb and resource and goes further than the title by stating the match rule: reference-number equality or contact-email substring. It never names the closest sibling (paginated_search_conversations) directly, instead pointing at the raw REST path `GET /api/v1/search/conversations`, so an agent must infer that this is the unpaginated variant.

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?

Usage is implied by the match semantics (use when you have a reference number or a contact email fragment) and the `conversations:read` prerequisite is stated. However, there is no explicit when-not guidance and no named tool alternative for filtered or paginated searching — the redirect is to an HTTP endpoint rather than a sibling tool, which is ambiguous inside an MCP context.

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