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

Annotations already declare readOnly=false, destructive=false, idempotent=true and closed-world, so the safety and retry profile is largely covered. The description adds one genuine behavioral fact beyond that: blocked/failed work stays active rather than being closed. It says nothing about required permissions, what state a successful completion transitions to, or concurrency behavior beyond what expectedVersion in the schema already implies.

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?

Three sentences, each carrying a distinct rule, with the state-preservation fact front-loaded right after the core action. Dense but not padded; no sentence is purely decorative.

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 7-parameter mutation with a nested details object, no output schema and version-based concurrency, the description covers success conditions but omits return/effect semantics and does not compensate for the misleading parameter docs. Adequate minimum, with clear gaps an agent would hit on first call.

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 100%, so the 3 baseline applies. The description does add one useful hint beyond the schema by tying details.status=resolved to finding resolution, but several schema descriptions are visibly wrong (taskId, details.status, sessionId and executionId are all documented as 'Owned project ID returned by list_linked_projects'), and the description does not correct that confusion.

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 'Record a versioned result' and gives conditional outcomes ('blocked/failed work stays active', 'Resolve a finding...'), which implies completion but never plainly states that this tool completes an inbox task. A named sibling like inbox_claim/inbox_start is not contrasted, so the agent must infer scope from the name alone rather than the prose.

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?

It supplies real conditional guidance: roadmap completion 'requires published meter advancement and confirmed evidence', and resolving a finding needs details.status=resolved plus a verification summary. That tells the agent when the call will succeed. It stops short of naming alternative tools or exclusions, so it is clear context without explicit routing.

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