search_messages

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

With no annotations, the description carries the full burden and does useful work: substring-match semantics (not full-text relevance), exclusion of activity messages, scoping to conversations the caller can access, and an explicit `messages:read` permission requirement. It omits result ordering and whether matching is case-sensitive, but the safety and scope profile is covered.

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 substantive sentences are front-loaded and tight, but the block is padded with two conflicting raw endpoint strings ('GET /api/v1/search/messages' and 'GET /api/v1/messages/search') plus a 'Tags: Search' artifact. That redundancy muddies rather than informs.

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 with no output schema, the access-scope and permission statements are the essentials and they are present. What is missing is any hint of return ordering or result shape, so an agent cannot predict what it will get back beyond 'messages'.

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 schema already documents `query` (minimum 3 chars) and `limit` (1–30, default 30). The description adds that matching is containment-based in message text, which is genuinely useful meaning beyond the schema, but says nothing about `limit` behavior and instead defers 'pagination' to an external endpoint that is not a callable parameter here.

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 ('Search Messages') and clarifies the matching semantics: messages whose text contains the query, activity messages excluded. It does not distinguish itself from the sibling 'paginated_search_messages', so the agent cannot tell from this text alone which of the two to pick.

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?

Implies usage ('Matches messages whose text contains the query') and points to 'GET /api/v1/search/messages' for filters and pagination, which hints at a heavier-weight alternative. However, it points to an API endpoint rather than a sibling tool name, so the routing guidance is not actionable in tool-selection terms.

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