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

Annotations cover only the safety profile (readOnlyHint, openWorldHint, destructiveHint, idempotentHint), and the description adds substantial extra context: the hybrid rule-based/AI pipeline, the ATSPrep guard that strips figures, names and tools absent from the user's text, and graceful degradation where the rule-based draft still returns with an explanation in ai.message. That is exactly the kind of failure-mode and data-handling disclosure annotations cannot carry.

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?

Purpose and mechanism are front-loaded in the first sentence, and the degraded-mode sentence is genuinely useful. The middle sentence spends considerable words on vendor/model names (Gemma 4, Llama 3.3 70B, Cloudflare Workers AI) that an agent does not need in order to select or call the tool.

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 no output schema, the description partly compensates by explaining that the response contains both a rule-based and an AI part and that ai.message carries the reason when the AI half is unavailable. It stops short of describing the overall response shape or field names, which is the remaining gap for a tool whose return value is undocumented.

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 both resume_text and target_title are already documented in the schema, and the description adds no format, length or interaction detail beyond what the schema states. Baseline 3 is correct when the schema does all parameter-level work.

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 verb 'Draft' and resource 'professional summaries from a resume' are specific, and the description further narrows scope by explaining the rule-based + AI composition. It never names a sibling (e.g. draft_cover_letter or generate_linkedin_headline), so differentiation is left to the resource name rather than stated explicitly.

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 text describes how the tool behaves but never says when to choose it over alternatives such as check_resume, tailor_resume or draft_cover_letter, nor any prerequisite beyond supplying resume text. Usage is only inferable from the tool name and first clause, which is the same gap that earned a 2 in the calibration example.

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