Validate feedback (raw text -> candidate tickets)

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

The description discloses key behavioral traits beyond annotations: uses deterministic keyword heuristics (no model calls), dry-run creates nothing, apply bulk-creates candidates, and allows passing an edited candidates array. It also mentions that the tool is idempotent in dry-run mode (but not in apply mode). This is highly transparent.

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 well-structured, front-loaded with the core purpose and key behavior. It is slightly verbose but each sentence provides necessary information. The length is justified by the complexity of the tool's two-phase workflow.

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 absence of an output schema, the description adequately explains the return value ('structured candidate list') and the two-phase process. It covers all important aspects: dry-run, apply, editing candidates, and the heuristic nature. No gaps in understanding the tool's behavior.

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 description adds significant meaning to parameters beyond the schema: explains that apply:false is the default and creates nothing, feedback is the raw text to parse, and candidates is an optional edited list for apply mode. It clarifies the workflow. However, the 'project' parameter lacks a schema description and the tool description does not elaborate on it.

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: parsing unstructured feedback into candidate tickets with a specific method (deterministic keyword heuristics). It uses a specific verb ('Parse') and resource ('unstructured feedback') and distinguishes from sibling tools by highlighting the bulk parsing from raw text and the two-phase dry-run/apply pattern.

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 provides clear usage guidelines: always dry-run first, then call with apply:true. It explains the default behavior and the workflow. However, it does not explicitly compare to sibling tools or state when not to use this tool (e.g., when feedback is already structured or when only one ticket is needed).

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