BidCraft

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

Annotations only declare the generic non-read-only/non-destructive/non-idempotent profile; the description adds the substantive behavior: a draft is saved rather than anything published, nothing is sent to any contractor by this tool, and the contractor contact happens only after the recipient clicks an emailed invite. That is exactly the side-effect and auth-flow context an agent cannot get from the schema or annotations.

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 usage trigger, then the outcome, then the downstream flow, then the data-hygiene rule — every sentence carries information an agent needs. It is slightly longer than necessary, with the 'nothing is sent to any contractor' line partially restating the invite-flow sentence.

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?

No output schema exists, and the description compensates by explaining the return value (a private link) and what happens after the agent hands it over. For a 5-param create tool with full schema coverage, nothing an agent needs in order to call it correctly or explain the result is missing.

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 baseline is 3; the description adds real meaning by telling the agent what must be omitted from the free-text title/description (street addresses, names, emails, phone numbers, budgets), which is a constraint the schema does not express. It adds no further guidance on city/state/zip beyond the schema.

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 quote request') plus the scope of what it produces: a saved draft and a private link. The workflow description (person opens link, supplies email, invite leads to BidCraft contacting contractors) makes it unambiguous how this differs from the read-only sibling get_quote_checklist.

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?

'Use after the person confirms the job description and asks to get quotes from local contractors' gives an explicit trigger condition and sequencing. It also gives a when-not constraint on content ('leave out street addresses, names, emails...'). It stops short of naming the sibling tool as an alternative, so it is clear context without full routing.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=false, and destructiveHint=false, so the safety profile is covered. The description does add the important geographic constraint (United States) and the intended downstream action (asking the person for the details), but with no output schema it should say more about the shape of what comes back.

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 usage trigger, with no filler. It is slightly indirect in the second sentence, where a direct statement of what is returned would have been tighter, but nothing is wasted.

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 one-parameter read-only tool this is close to sufficient, and the annotations carry the safety story. The main gaps are the unspecified return shape (no output schema exists) and no pointer to create_quote_request as the follow-up step.

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?

There is a single parameter with 100% schema coverage, including an example ('replace a roof'), so the baseline is 3. The description adds only domain framing ('building, repair or renovation work'), not anything about how specific or granular the job string should be.

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 frames when the tool is used and hints at a return value ('the details contractors need'), but never states plainly that it returns a checklist of information fields for a quote. A reader can guess the resource from the name and the second sentence, but the description itself never commits to a concrete verb+object.

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?

'Use when someone wants quotes for building, repair or renovation work in the United States' gives a usable triggering context. However, there are no exclusions, and the only sibling, create_quote_request, is never mentioned even though the natural workflow is to gather the checklist then create the request.

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