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

The description states that using scope 'spec' writes a new snapshot and may raise alerts, which is a side effect. However, the annotations declare readOnlyHint: true, directly contradicting that statement. This is a serious inconsistency that misleads the agent about the tool's side effects.

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 reasonably concise and well-structured, covering the essential behavior, scope options, and the side-effect warning. The caveat about 'not a free read' adds important information but is slightly verbose.

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 description provides enough context for the agent to understand the tool's purpose, scope options, parameter requirements, and side effects. It does not include an output schema, but the description sufficiently indicates what kind of result to expect (average, trend, breakdown).

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?

The schema has complete descriptions for both parameters. The description further clarifies that specId is required for scope 'spec' and that it is a public GUID. The default behavior of scope is also stated.

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 clearly states that the tool gets a governance quality score, and explains the two scopes: 'org' provides an average across specs with trend and per-spec breakdown, while 'spec' targets a single spec. This distinguishes it from other get_* tools.

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 explicitly explains default scope 'org', the need for specId when scope is 'spec', the project-context requirement, and warns that the 'spec' scope recalculates the score and is not a free read. This gives clear guidance on when and how to invoke the tool.

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