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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the bar is lower; the description still adds the crucial trait that output is heuristic candidates rather than confirmed findings. The 'imported repository' prerequisite is also disclosed. It omits cost/latency expectations for scanning a whole repo, which is a meaningful gap for an open-world read.

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 core action and scope are front-loaded, and the enumeration of candidate types is compact and load-bearing. The single long compound sentence is dense but not padded; a light reflow would improve scannability without changing 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?

With an output schema present, return values need not be explained, and the description correctly focuses on candidate provenance and interpretation caveats. It is nearly complete for a two-parameter tool, lacking only explicit guidance on repo_url form and what to do if the repository has not yet been imported.

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 0%, so the description must carry parameter meaning. It does well for `query` by giving three concrete example strings that convey the expected granularity of a bug-kind phrase, but `repo_url` is only indirectly implied via "imported repository" and its format/relationship to hokmah_connect_project is never stated.

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 uses a specific verb+resource pair ("finds past fixes ... and the current files where the same defect may still exist") and enumerates the three candidate categories it produces. Concrete example queries ("null run data guard", "prototype pollution", "race condition on resume") make the intended input unambiguous and distinguish it clearly from siblings like hokmah_analyze or hokmah_overview.

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?

"in an imported repository" establishes a prerequisite, and the closing sentence "Read each candidate with the fix in mind; a candidate is not a confirmed bug" tells the agent how to treat results. It stops short of naming alternatives or stating when a sibling such as hokmah_analyze should be preferred instead.

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