Review Dialogue Candidates

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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds genuine behavioral context beyond them: local-only processing, no transcription or timeline mapping, and stale-selection rejection when a review revision changes. It does not, however, explain error behavior or limits beyond the schema.

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 tightly packed sentences with the primary purpose front-loaded ahead of the stale-revision and scope caveats. Every clause conveys information; nothing is padding.

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 an 8-parameter tool with a full output schema and complete parameter coverage, the description need not explain return values, and it correctly focuses on workflow (revision staleness) and scope boundaries. The main gap is the absence of explicit routing against sibling review/analyze tools.

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 schema already documents all eight parameters thoroughly. The description loosely maps to them ('silence padding', 'keep/reject decisions', 'surrounding words') but adds no syntax, format, or constraint detail beyond what the schema provides. Baseline 3 is appropriate.

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 and resource (review dialogue candidates) and describes the computation performed: surrounding words, silence padding, keep/reject decisions, and unioned removal duration. However, it never names its closest sibling (analyze_dialogue_edit_candidates) or the other review_* tools, so the agent must infer the boundary from the 'Local-only' clause rather than an explicit distinction.

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 'Local-only; no timeline mapping, transcription or mutation' clause gives real negative guidance about what this tool is not for, and 'Recomputed review revisions reject stale selections' hints at the initial-review-then-select workflow. But there is no explicit when-to-use statement or named alternative, leaving the agent to infer usage from the description.

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