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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so safety is covered structurally. The description adds meaningful context that output is editable and nothing is persisted, which reinforces but does not extend far beyond the annotations; nothing is said about auth prerequisites or what the draft contains.

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 dense sentences, front-loaded with what the tool produces and immediately followed by the action/endpoint/body contract. The 'draft: POST /v1/check/draft' notation is compact but borders on shorthand that requires inside knowledge.

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 tool with a nested body object, 11 parameters and no output schema, the description covers the essential body fields but not how the auxiliary parameters (identity, idempotency, credentials) apply to this action. An agent can draft correctly only if it guesses the rest from the schema.

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 9%, so the description carries real weight here. It does explain the body contents (required 'need', optional 'columns'), which the schema only punts to OpenAPI, but the other ~10 parameters (id, handle, token, idempotency_key, agent_key, etc.) are left entirely undocumented.

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 result: draft editable machine checks from requirements and column names. It also distinguishes itself from the checking siblings (provider_check_request, check_received_work) by saying it does not check or store a delivery. Slightly cryptic phrasing ('machine checks') but the operation is identifiable.

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?

The clause 'without checking or storing a delivery' implies this is a pre-flight/draft step before a real check, but no sibling is named and no explicit 'use this when X instead of Y' guidance is given. Usage is inferable rather than stated.

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