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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description does add a genuine behavioral fact beyond the annotations: unknown input returns the list of available use cases rather than failing, which is a non-obvious probe/discovery behavior. It does not describe result formatting or ordering, but with annotations carrying the read-only profile a 3 is fair.

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?

Two sentences, zero filler, with the core purpose front-loaded and the discovery fallback placed second. Every sentence carries information an agent needs.

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 single-required-param read tool with no output schema and full schema coverage, the description is nearly sufficient: purpose, value vocabulary, and the unknown-value behavior are all present. A brief note on what the returned list contains (server entries vs. prose) is the only notable omission.

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 goes further by showing the accepted slug vocabulary (client names and topic slugs) and defining the out-of-vocabulary behavior for use_case. That meaningfully expands on "Use-case slug or name" in the schema.

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: return the curated "best MCP servers for X" list for a use case or client. The word "curated" is a meaningful distinguishing signal against the search_servers sibling, but no sibling is named explicitly, so an agent must infer the contrast.

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 context (use case or client slug) plus concrete value examples ("claude-code", "jira", "postgresql", "web-scraping"), and a useful negative-path rule: call with an unknown value to enumerate available use cases. It stops short of stating when to prefer this over search_servers or list_categories.

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