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

Annotations only declare readOnly=false, destructive=false, idempotent=false; the description goes well beyond that with async semantics, the offer_id/get_offer handoff, per-plan quota accounting, the profile fallback for missing country, and five named error outcomes. This is exactly the behavioral context 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?

Front-loads purpose, then the verbatim-input constraint, then async behavior and the get_offer follow-up, then parameters, then quota and error codes. It is dense but every sentence carries new information; nothing is padding.

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 async, quota-metered write tool with a referenced schema and an output schema, the description covers invocation, retrieval of results, fallback behavior and failure modes. An agent has everything needed to call it and interpret the response.

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 nested schema already describes all five fields well, but the description still adds meaning: vacancy_id links the offer to the tracker, countries default to the profile when omitted, and source_text loses extracted numbers if paraphrased. The only gap is that it doesn't surface the employment_type enum values, which the schema does.

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+resource ('Analyse a job offer ... draft the negotiation scripts') and immediately distinguishes it from the vacancy/radar siblings by scoping to a received offer. An agent can tell this apart from analyze_vacancy and analyze_tracked_vacancy 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?

Clearly says the source text must be verbatim wording from the recruiter and that summarised text loses the numbers, and it routes the agent to get_offer(offer_id) for the result. It also says when to pass optional fields ('when the user said them'). It lacks an explicit 'use X instead' for the vacancy-analysis siblings, so it stops short of a 5.

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