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

Annotations declare readOnlyHint=true, and the description reinforces this with 'Free, read-only, no signup.' Beyond that, it discloses the grading methodology (reachability and real content), the return contents (grade, last-audited time, longitudinal trend, cite line, ed25519-signed record), and the philosophical stance ('measurement only, not endorsement'). It adds meaningful behavioral context that annotations alone do not convey, and it does not contradict the 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?

The description is longer than average but front-loads the core purpose and follows a logical structure: purpose, context/methodology, return contents, and alternatives. Every sentence adds value, though it could be tightened (e.g., the marketing tone around 'verifiable evidence and history' is somewhat verbose). Still, given the tool's complexity, the length is justified.

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 no output schema, the description must explain return values, and it does: it lists the top live endpoints, grade, last-audited time, trend, cite line, and signed record. It also covers usage context, grading criteria, and alternatives. For a read-only recommendation tool with 3 optional parameters, this is as complete as an agent needs to call it correctly.

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. The description adds value by clarifying the default behavior when `need` is omitted ('Omit to get the endpoints with the highest measured readiness grades overall'), providing concrete keyword examples ('payments', 'search', 'github', 'postgres'), and explaining the grade semantics in context. These are not present in the schema, so the description enriches parameter understanding beyond what the schema provides.

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 opens with a clear verb-object-purpose: 'Get SaSame-observed MCP server recommendations for a capability you need.' It distinguishes the tool from siblings by framing it as measurement-only (not endorsement) and by naming alternatives (claim_start, engage_sasame). The resource and goal are unambiguous.

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?

The description gives explicit when-to-use guidance and directly names alternatives: 'If you operate one of these servers, claim it (claim_start). If you can't find a fit and need an MCP/agent BUILT, call engage_sasame.' It also explains how to pass a referral handle from `refer` to engage_sasame, and when to omit the `need` parameter. No ambiguity remains about selection.

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