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

With no annotations, the description carries the full burden and does so: it discloses the grounding enforcement ('Every claim is checked against the resume'), the failure mode (`ungrounded`), that unsupported claims are stripped, side-effect freedom ('Nothing is submitted'), and the pricing/quota constraint ('Free on every tier; monthly AI quota applies'). That is auth/cost/safety/destructive-behavior coverage in one paragraph.

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?

Five short sentences, front-loaded with purpose, then grounding behavior, return values, the non-submission guarantee, and cost. No sentence is redundant with another and the most decision-relevant fact (no submission) is placed where it will be read.

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?

There is no output schema, and the description compensates by naming the return payload (apply URL, optional reply-to address) and the `ungrounded` failure. Gaps remain around quota consumption on regeneration, whether a re-draft overwrites a prior draft, and idempotency, but the essentials for correct invocation are present.

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 `id`, `parts`, and `locale` are already documented with defaults and examples. The description adds only general framing ('for one job', 'from the key owner's saved resume') and mentions an optional reply-to address, but nothing about `parts` selection trade-offs or `locale` behavior beyond the schema. Baseline 3 applies.

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?

Specific verb and dual resource ('Draft a grounded cover letter and a tailored plain-text resume') scoped to 'one job' from the owner's saved resume. The line 'Nothing is submitted — the seeker applies by hand' cleanly separates it from the write-oriented sibling apply_to_job, so an agent can route without opening the schema.

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?

Usage context is clear: drafting one application package against one job, with the explicit exclusion that nothing is submitted, which implicitly routes submission elsewhere. It does not name apply_to_job directly or state prerequisites (e.g., whether the seeker must already have a saved resume), so it falls just short of full when/when-not/alternative coverage.

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