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

Goes beyond the annotations by explaining the actual idempotency semantics ('A second call for the same job sends nothing and names the first application') and by disclosing the required auth scope (bewerbung:senden) and consent framing. What it doesn't cover is failure behavior or what an omitted attachment defaults to beyond 'the user's resume', which keeps it from a 5.

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?

Front-loaded with the trigger condition and generally tight, but 'explicitly wants it sent' and 'explicitly asked to send it' restate the same consent rule twice, which is mild redundancy rather than waste.

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 an irreversible outbound-email mutation, the description supplies the consent gate, the idempotent-repeat behavior, the auth scope, and the attachment payload — and an output schema already covers return values. Nothing an agent needs to call this safely is missing.

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 the load. It does clarify anschreiben (cover letter) and anhang (resume document or another PDF), but stelleId is never explained (presumably the job from get_job_matches) and the optionality of anhang is only implied.

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?

States a specific verb and resource ('Sends exactly one email to the employer') plus the payload (cover letter + resume/PDF attachment). It is clearly distinguished from the sibling draft_job_application by the 'sent vs. draft' framing, so an agent can pick correctly without opening a 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?

Gives an explicit precondition ('after they have seen the draft and explicitly asked to send it'), which doubles as a when-not rule: don't call while the draft is unseen or unsent-requested. It also names the consequence-based stop condition for repeat calls, leaving little to inference.

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