decision_refresh

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

The annotations indicate this is a mutating tool (readOnlyHint=false) but not destructive (destructiveHint=false). The description goes beyond this by clarifying that content is not mutated, only metadata, and that adding evidence appends a dated entry without overwriting. It also discloses a side effect: transitioning away from 'superseded' automatically clears the dangling superseded_by pointer. This provides useful behavioral context beyond the annotations, though it does not cover all possible edge cases (e.g., invalid decision_id).

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?

The description is concise and well-structured. It opens with a clear verb and resource, lists the three main actions, and then provides two critical usage notes in separate sentences. Every sentence earns its place, and there is no fluff or repetition of schema content that is already obvious. The length is appropriate for the tool's complexity.

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?

Given the tool's moderate complexity (4 parameters, one required, no output schema), the description is mostly complete. It explains the core functions, the distinction from decision_log, and the special superseded status rule. However, it does not mention what the tool returns (e.g., success confirmation or updated decision object) or how errors are handled (e.g., nonexistent decision_id). Since there is no output schema, a brief note on the return value would have been helpful, but the tool remains usable with the information provided.

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?

The input schema describes all four parameters with 100% coverage, so the schema already provides the heavy lifting. The description reinforces the meaning of 'add_evidence' (append, never overwrites) but does not add substantial new meaning beyond the schema. The 'status' parameter's special handling is also documented in the schema, so the description's reference to it is redundant but consistent. As per the baseline rule for high schema coverage, a 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?

The description clearly states the tool's purpose: refreshing metadata for an existing decision, listing specific actions (bump review_date, append evidence, change status). It distinguishes itself from related tools like decision_log by explicitly noting it does not mutate decision content, and for content changes, a new decision should be logged. The verb 'Refresh' plus resource 'decision metadata' is specific and unambiguous.

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 description gives explicit usage direction: 'Use INSTEAD of editing decisions.json directly' and 'for content changes, log a new decision via decision_log.' It also provides a conditional rule for the 'superseded' status, stating this should only be used when a replacement decision exists and advising to prefer decision_log with the 'supersedes' parameter. This is clear when-to-use and when-not-to-use guidance with specific alternatives.

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