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

Annotations declare readOnlyHint=true and openWorldHint=false, and the description adds substantial context beyond them: the A/B/C/D grading methodology (reachability + real content), that results carry a longitudinal trend, a ready-to-quote attributed cite line, and an ed25519-signed offline-verifiable record. It also states cost/auth profile ('Free, read-only, no signup') and disclaims fabricated demand/revenue and custody.

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 purpose and routing are front-loaded, but the long middle clause about SASAME S.R.L., GEC, Outcome Demand discovery, Exchange, Observatory and Factory capabilities, and 'no fabricated demand/revenue and no custody' is corporate boilerplate that does not help an agent select or invoke the tool. The signed-record and trend detail could be trimmed without losing selection value.

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?

There is no output schema, and the description compensates by enumerating what each result contains (endpoint, grade, last-audited time, trend, cite line, signed record) plus defaults and limits. What an agent needs to call and interpret results is largely present, with only minor gaps around pagination or ordering beyond grade.

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 100%, so the schema already documents `need`, `limit` (default 5, max 10), and `min_grade` (default B). The description only restates the keyword-filter idea ('optionally filtered by an endpoint keyword') without adding format, matching, or edge-case guidance, so the baseline of 3 applies.

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+resource ('Get SaSame-observed MCP server recommendations') and narrows the scope to a capability need, with an explicit note that it returns 'top live, real-content endpoints' with grades and last-audited times. An agent can distinguish this from siblings like audit_mcp, verify_mcp_ready, or ecosystem_search without opening the schema.

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 ('pick a measured MCP candidate instead of guessing') and routes adjacent intents: claim_start if you operate a listed server, engage_sasame if no fit exists and you need something built. It does not, however, explicitly say when to prefer this over the other discovery-ish siblings such as ecosystem_search or capability_landscape, so no exclusion criteria are provided.

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