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

Annotations already cover safety (readOnly, idempotent, non-destructive, open-world), and the description adds substantial behavior beyond them: the static shard keyed by sha256 of the normalised URL, the NOT_MEASURED-with-empty-list contract ('never an error and never a clean bill'), the explicit absence of verdicts/scores/rankings, and the inclusion of Merkle root and inclusion pointer for independent verification.

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?

Front-loaded with the operative framing ('Trust per server, not totals') and every sentence carries information rather than filler. The first sentence is very long and packs a parenthetical enumeration of dimensions, which costs some readability but does not waste space.

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?

The tool has an output schema, so return values need no prose, yet the description still covers the empty/absent case, the state taxonomy fields, and verification affordances. Nothing an agent needs to call this correctly is missing.

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 adds real semantics by explaining the URL is normalised and hashed to select the shard, implying case/trailing-slash variants resolve to the same capsule set. That goes beyond the schema's format/pattern constraints.

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 precise verb+resource ('every published measurement capsule about ONE endpoint URL across all batches') and enumerates the capsule families returned, which clearly separates it from aggregate siblings like board_totals and from verify_* tools that validate a single capsule. An agent can tell it apart from the other evidence tools 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?

'Trust per server, not totals' implies it is the per-endpoint counterpart to the totals tools, which gives useful framing. But no alternative tool is named and no explicit when/when-not condition is stated, so routing versus mcp_trust, measurement_index or verify_capsule is left to inference.

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