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

Annotations already include idempotentHint=true and destructiveHint=false, but the description adds significant behavioral detail: it does not post on behalf, runs the draft through screening screens, and returns failure reasons if the draft is vague, advert-like, or matches scam patterns. This goes beyond the structured annotations by explaining the internal validation process and the exact nature of the output (a reviewable link or reason). No contradiction with annotations.

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 longer than a single sentence but every clause serves a purpose: it states the action, the non-action, the screening behavior, and the input guideline. It is front-loaded with the core benefit (drafting and returning a link) and then adds crucial nuances. While it could be tightened slightly, the structure is logical and no filler exists.

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 a tool with no output schema, the description effectively describes the return value (a link the homeowner opens, or a reason for failure) and the behavioral constraints. It covers the essential context an agent needs: what to provide (job description), what the tool will not do (post), and what happens during screening. Given the complexity of the screening process, the description is remarkably 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 coverage is 100%, so all parameters have descriptions. The description adds extra semantic guidance for the 'description' parameter, instructing the agent to describe the job 'in the homeowner's own words: what needs doing, where on the property, and roughly how big.' This enriches the schema's terse requirement ('The job in the homeowner's words') with practical content expectations. The other parameters are adequately covered by the schema, so this is a modest bonus above the baseline.

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 primary action ('Draft a job post for a homeowner') and its outcome ('get back a link THEY open to review and post it'). It also clarifies what it does NOT do ('never posts on anyone's behalf'), distinguishing it from sibling tools that are primarily read/browse operations. The resource and verb are specific, leaving no ambiguity about the tool's function.

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 context on when to use this tool: to draft a job post that the homeowner will later post, emphasizing that it does not actually publish. It implies that this is the appropriate tool for drafting rather than posting directly. However, it does not explicitly name alternatives or state conditions under which another tool should be chosen, though the sibling list shows no competing drafting tool. The guidance is clear but not exhaustive.

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