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

Annotations already declare not read-only, not idempotent, not destructive. The description adds the useful detail that a revision is 'observed' (optimistic concurrency against expectedRevision), but it doesn't say what happens on a revision mismatch, whether the save is rejected or overwrites, or what state results.

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 short sentences with the payload contents front-loaded before the prerequisite. No wasted clauses, though the second sentence reads as an instruction rather than definitional content.

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 nested, multi-object mutation with no output schema and only partial schema coverage, the description leaves the response shape, revision-conflict behavior and the role of compositionId/transitionIntent unstated. Adequate to attempt a call, not to predict its outcome.

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 67% and the description maps its prose onto selectedFindingIds, omittedReasons, unresolvedGaps and the observed revision, which helps. However compositionId, compositionVersion and transitionIntent are documented nowhere, and the body/runId duplication is unexplained.

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 (save) and enumerates the resources being persisted: selected finding IDs, omitted reasons, unresolved gaps, tied to an observed run revision. That is distinguishable from editorial_findings_append and editorial_apply, though it never explicitly names those siblings.

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?

'Read the run and findings before deciding' gives a prerequisite ordering, which implies the editorial workflow, but it never says when to pick this over editorial_apply or editorial_findings_append, nor what conditions make integration appropriate.

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