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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds value beyond that: it discloses exactly what is diffed, the 'echo both revisions for subsequent pages' pagination behavior, and the v1/mixed-format handling nuance.

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 core action, then layered with report contents and edge cases; sentences are dense but each carries signal. The v1/mixed-format clause is slightly specialized, but overall there is little waste.

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 does most of the work by naming the reported fields and echo/pagination behavior, and annotations cover the read-only nature. The remaining gap is that the two nested revision parameters are left undescribed, but for a read-only compare tool the definition is largely complete.

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 only 20% (only projectId is documented) and both nested revision objects have undescribed required fields (outputJobId, payloadHash). The description indirectly implies the two revision inputs ('current draft', 'previous saved revision') and pagination ('subsequent pages'), but gives no syntax or semantics for the revision hash/outputJob objects.

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 (compare) and precise resources (current draft vs. previous saved revision in the same dossier), then enumerates what it reports (added/removed/changed answers, question/constraint, frozen-evidence changes). An agent can tell this diff tool apart from siblings like check_draft or read_draft_review without opening any 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?

Provides explicit scope exclusions — 'No decision is transferred; this is not source freshness or approval' — which help route the agent away from adjacent concerns. It does not name specific alternative tools or a positive 'use this when' trigger, so it stops short of full when/when-not/alternatives guidance.

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