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

Annotations already establish a non-idempotent write to a closed-world system, so the bar is lower. The single added behavioral fact, "It is kept with a reference number," is genuinely useful because there is no output schema and it tells the agent what to expect back. It says nothing about validation failures, duplicate submissions (non-idempotent but no de-duplication guidance), or that contact data is stored separately and purged after 180 days, which is the kind of side effect an agent should disclose before sending personal data.

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 short sentences, front-loaded with the action and ending with the useful retention detail; nothing is padded. The brevity is efficient rather than bloated, though it shades into under-specification for a 10-parameter tool.

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?

This is a mutation with ten parameters, four nested objects, an enum, and no output schema, yet the description covers only the barest outline. It omits required-field meaning (slug, need), how specifications relate to the service's request schema, and the contact-data retention policy, so the definition is not complete enough for correct invocation without reading the schema closely.

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?

With 10 parameters at only 40% schema description coverage, the description carries the burden of explaining meaning and contributes nothing about any parameter. The undocumented ones are the consequential ones: the 'action' enum, the 'requested_fields' array (max 30), the 'specifications' bag of fields drawn from the service's request schema, and the budget/timing/quantity/geography nested objects. The crucial hint that slug accepts 'anything-else' appears only in the schema, not the description.

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 gives a specific verb and resource ("Send a requirement to one of Chamfer's services"), which is distinct from the read-oriented siblings list_propositions and describe_proposition. However, it introduces 'requirement'/'service' terminology that does not match the sibling vocabulary of 'proposition', and it never explains what a 'requirement' actually is, so the agent must infer the domain.

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?

There is no when-to-use guidance beyond the implied write action, no mention of preconditions (must the service slug exist first? is describe_proposition needed first to learn the request schema?), and no exclusions against alternatives. The agent is left to infer that this is the submission counterpart to the two read tools.

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