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

The annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. Beyond that, the description adds genuinely useful context: the dual authorization requirement (tenant Owner plus platform administrator) and the explicit assurance that reading performs 'no approval or execution', which prevents an agent from assuming the read advances the workflow.

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 sentences, front-loaded with what is read, followed by prerequisites and the safety caveat. Nothing is redundant, and the ordering matches how an agent would evaluate the call. Density of jargon keeps it from a 5.

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 correctly summarizes the returned content (proposal, diff, proof, consumption and delivery state) and adds authorization and no-side-effect caveats, so the workflow context is reasonably complete. The notable gap is the undocumented jobId parameter, which is the one thing an agent must get right to invoke the tool.

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?

There is a single parameter, jobId, and schema description coverage is 0%, so the description carries the full explanatory burden. It never mentions jobId, its '^codingquality-[a-f0-9]{64}$' format, or whether it is required (required count is 0). An agent gets the parameter's existence only from the schema, with no semantic framing from the description.

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 specific verb and resource: 'Read the same verified code quality proposal, exact diff, proof, consumption and delivery state'. That tells an agent exactly what comes back, and the distinctive resource name means no sibling in the list competes with it. It falls short of 5 only because phrases like 'consumption and delivery state' and 'verified' are domain jargon rather than plain statements of content.

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 a prerequisite ('Requires the current tenant Owner and platform administrator') and a downstream instruction ('use the returned policy and its existing human approval card'), which is real guidance. However, it never states a when-to-use condition or names any alternative tool, so the agent must infer the triggering situation from the tool name alone.

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