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 that step 1 only validates and returns a summary, consent line and token; that submission happens only on step 2 with the token; and that an email link must be clicked before any provider sees the enquiry. The definition of consent is spelled out verbatim, which is essential for a tool that sends personal data onward.

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 disambiguating scoping statement, then cleanly organized as Step 1 / Step 2. Dense but every clause is load-bearing; the only minor cost is the quoted consent sentence, which lengthens the text but is functionally necessary.

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 a nested-object, two-phase write tool with no output schema, the description fully covers inputs, the return of step 1 (summary, consent line, token), the gating condition, and the downstream email-confirmation behavior. An agent has everything needed to run both calls correctly.

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 coverage is 100%, so the baseline is 3, but the description goes beyond the schema by explaining sequencing: 'answers' must be keyed by field key from enquiry_fields, 'consent=true' is required in both calls, and 'confirmation' is the token from step 1 used only in step 2. That conditional presence of the token is real semantic value the schema alone does not convey.

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 ('Submits an enquiry to Calcul Brut en Net') and immediately scopes it with two negations ('NOT a purchase, NOT a guaranteed quote'). This clearly separates it from the dataset_* siblings and from the read-only enquiry_describe/enquiry_fields helpers.

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?

Explicitly prescribes the two-call sequence, the condition that gates step 2 ('only if the person agrees'), and what to do with step 1's output ('show the person the summary and the consent line'). Nothing about when to invoke it is left to inference.

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