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

Annotations already establish read-only, idempotent, non-destructive behavior, so the description's added value is the matching semantics ('lexical/bilingual'), the filter strictness ('unknown auth or price is not satisfied'), the deployment default ('Defaults to remote endpoints'), and cursor replay instructions — all real behavioral context beyond the annotations. Return shape and ranking order remain undisclosed.

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?

Four short sentences, front-loaded with the core purpose and no filler. Density is high, though 'unknown auth or price is not satisfied' is terse to the point of needing a reread given there is no price parameter.

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?

With 7 undescribed parameters and no output schema, the description covers matching, defaults, and pagination but omits how 'q' relates to 'task', what 'limit' controls, and what the transport/deployment enums actually select. Adequate to start a call, not sufficient to call it optimally.

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% across 7 parameters, so the description carries the full burden; it clarifies only 'after' (follow next_cursor with identical query and filters), the deployment default, and implies require_no_auth through the auth-strictness sentence. It adds nothing for 'q', 'limit', 'transport', or the task enum values, leaving the majority of parameters unexplained.

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 concrete verb and resource ('Discover publicly listed MCP services') plus the scope qualifier 'for a task', and distinguishes itself from recommendation-style tools via 'publisher metadata, not tested recommendations'. It never names a specific sibling such as match_service_task or get_service, so an agent must infer the boundary rather than being routed explicitly.

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 a clear use context (finding public MCP services for a described task) and an implicit exclusion via 'not tested recommendations', plus the operational rule that unknown auth or price does not satisfy the filter. It stops short of stating when to prefer the recommendation/matching siblings instead.

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