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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), but the description adds real value beyond them: it enumerates the possible states (not_started, reading, asking, thinking, done, later, failed) and the payload contents (waiting questions with keys/options, counts, prior reads, save timestamp). It also discloses a domain constraint — Tommo Legal does not start until the profile exists. It does not need to cover auth/rate limits for a parameterless read.

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?

Two sentences, front-loaded with what the resource is before the field-level list of what is returned. It is dense and peppered with internal codes (ONB-02.4, LEGAL-04.3), which adds jargon overhead, but there is no filler or repetition.

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 and no parameters, the description carries the burden of explaining the return payload, and it does so field-group by field-group (state, pending questions, counts, prior reads, save time). Combined with annotations that already declare read-only/idempotent behavior, an agent has enough to call it correctly; only the missing sibling contrast keeps it short of 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?

The tool takes zero parameters, so there is nothing for the schema to document and the baseline is 4. The description appropriately describes only the returned content rather than inventing inputs.

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 defines the resource ("Your contract positions" / the cold-start interview) and states what a caller gets: the interview's state, pending questions, ask/answer counts, prior reads, and save time. That makes the read purpose clear, but it never names or contrasts the obvious sibling operations (start_the_contract_positions, answer_the_contract_positions, do_the_contract_positions_later), so differentiation is left to inference.

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 is only implied by the phrase "Where the interview stands" — a caller can infer this is the status-check tool, but there is no explicit when-to-use, no prerequisites, and no statement of when to prefer it over the start/answer/do-later siblings. Adequate but leaves routing to inference.

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