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 adds the scoring dimensions and the ruleset caveat, but says nothing about the report structure, pass/fail thresholds, or what happens when a document is unscoreable — gaps that matter for a diagnostic tool with no output schema.

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 tight sentences that front-load the core action and output before the ruleset advice. The second sentence is slightly rhetorical ('a score against rules you never adopted means little') but it carries real guidance, so little is wasted.

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 read-only scoring tool with annotations carrying the safety profile and no output schema, the description covers the dimensions and the customization path adequately. It leaves the response format and edge-case behavior unstated, which is a minor gap rather than a blocking one.

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 `document` and `context` are already fully documented, which sets the baseline at 3. The description introduces a `ruleset` argument that does not appear anywhere in the input schema, which adds a little semantic color but also creates ambiguity about how it is supplied.

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 (score) and resource (API maturity) plus the exact output shape: a 0-100 number with a letter grade. It also enumerates the scored dimensions (design, governance, documentation, discoverability, agent-readiness, operations), so an agent knows the breadth of the operation without opening the schema. This is well differentiated from narrower siblings like api_coverage or governance_report.

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 one usage cue — supply your own `ruleset` so the score reflects adopted rules — which is a prerequisite-style hint rather than a when-to-use statement. It never says when to pick this over api_coverage, governance_report, or score_reusability, so the selection guidance is only implied.

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