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

Annotations only declare destructiveHint=false, so the description carries most of the burden and does well: it flags this as a WRITE, clarifies the record is created in draft state and no email is dispatched, and surfaces the uniqueness constraint on statement_no. It does not say what is returned (e.g. the new estimate id) needed for chaining to send_estimate.

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?

Three compact fragments with the WRITE marker front-loaded, then behavior, then constraint, then endpoint. Every clause carries information and nothing is padded.

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 14-parameter creation tool with no output schema, the description covers intent and the email-suppression behavior but omits what the call returns (the created estimate's id) and gives no shape guidance for the many optional line-item arrays beyond what the schema already says.

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 79%, so the baseline is 3. The description's 'statement_no must be unique' reinforces rather than adds to the schema's own 'Unique estimate number' text, and it says nothing about the 14 parameters — line types (items/tasks/trips/expenses/discounts/taxes), date formats, or which fields are conditionally expected.

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 ('create an estimate'), disambiguates the business term with the alias 'quote', and scopes it to a connection. The 'starts as a draft, nothing is emailed' clause distinguishes it from send_estimate without naming it.

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?

'Starts as a draft, nothing is emailed' gives the agent the key operating condition and implies the send_estimate follow-up, and the endpoint reference frames it as the POST-only creation path. It stops short of explicitly naming hiveage_send_estimate or hiveage_create_invoice as the alternatives.

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