analyze_pr_feedback

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

With no annotations, the description must carry the behavioral burden; it discloses the 'analyze' access level and the returned JSON keys, which is useful. However, it omits the key behavioral dependency (what happens when no prior audit_pr record exists) and does not confirm read-only versus mutating behavior.

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 tight sentences with the core action front-loaded, followed by access level and return shape. Efficient and well-ordered, with 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?

An output schema exists, so the return-key enumeration is somewhat redundant, and parameters are fully documented in the schema. The remaining gap is behavioral: with no annotations, the description should state the missing-audit-record case and read-only nature to be complete.

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 baseline is 3. The description adds only marginal value by clarifying that pr_ref/project_id must match the original audit_pr call; no format or edge-case detail beyond the schema is supplied.

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 (link/classify) and resource (PR review feedback linked to the most recent audit_pr record), and names the exact keys used for matching (pr_ref/project_id). It is distinguishable from audit_pr because it is explicitly the consumer of that record, though it does not differentiate itself from the broader query/classify 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?

Implies usage via 'for the calling LLM to classify each feedback point,' making the context inferable, but it never states when to use this versus audit_pr, query_rules, or check_feature_against_rules, nor any prerequisite that an audit_pr call must have happened first.

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