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

Adds rich context beyond annotations: exact side effects of each action (use → new version with current kept/restorable and re-enters review; keep → version untouched; both resume paused schedules), plus explicit refusal conditions. This meaningfully elaborates the destructiveHint/idempotentHint profile with what gets destroyed or preserved.

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-loads the purpose and discovery step, then action semantics, then refusal conditions. Dense but every clause earns its place; no filler.

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 mutation tool with no output schema, the description covers preconditions, both action branches, post-conditions (review re-entry, schedule resumption, restorability), and error conditions. Complete enough to call correctly without further docs.

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 100% and the enum param is already documented in the schema, so baseline is 3. The description adds value by explaining the semantic distinction between 'use' and 'keep' in flow terms (fresh approval, paused schedule), which goes beyond the schema's terse enum descriptions.

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 (resolve) and resource (a proposed correction), and clearly names the sibling it depends on for discovery (get_post's `proposal` field). Distinguishes itself from approve_post/review_post by being the resolution step for a Rebbel-proposed correction.

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?

Explicitly says when to call: after get_post shows a proposal and the user has picked. Also names the two alternative actions (use vs keep) and their outcomes, and lists refusal conditions. Leaves nothing to inference.

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