site

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

With no annotations, the description carries the full burden and does well: it states that nothing is bought, ordered, or paid, that no quote is guaranteed, that it is free, and that it returns who receives details, consent wording, and confirmation. This goes well beyond a mere summary of the tool's action.

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?

The description is short, front-loaded with the 'Read first' instruction, and every sentence contributes meaningful caveats or return-value information. There is no redundant or filler content.

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 zero-parameter informational tool, the description covers purpose, usage timing, behavioral caveats, and what information is returned. It does not detail the exact response format, but that is likely unnecessary for this simple reference tool.

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?

The tool has zero parameters and schema coverage is 100%, so the baseline is 4. The description appropriately provides no parameter-specific detail because there are no parameters to document.

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 identifies the tool as a read-first explainer for submit_enquiry on M365 Migration Cost, using the specific verb 'states plainly' and naming the exact resource and context. It distinguishes itself from submit_enquiry by clarifying the tool is informational, not the action itself.

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 imperative 'Read first' clearly tells the agent to consult this tool before using submit_enquiry. It also explains what submit_enquiry is not (no purchase, no guaranteed quote), which helps prevent misuse, though it does not explicitly compare against the sibling enquiry_fields.

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?

With no annotations, the description carries the full burden of behavioral disclosure. It makes clear what data is returned (keys, labels, types, required flags, help text, options) and implies a read-only metadata lookup, but it does not explicitly state absence of side effects, authentication requirements, or error behavior.

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?

One dense, well-structured sentence front-loads the resource and then enumerates the returned field properties, ending with practical downstream guidance. No unnecessary words and every clause contributes meaning.

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 zero-parameter metadata lookup with no output schema, the description fully specifies what will be returned and how the result should be used with submit_enquiry. The lack of explicit mention of enquiry_describe is a minor omission and does not undermine the tool's completeness.

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 are zero parameters, so the description appropriately provides no parameter instructions. The relevant cross-tool guidance about passing answers to submit_enquiry keyed by field key adds useful context beyond the empty schema, matching the baseline for a no-parameter tool.

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 states that the tool returns every field of the M365 Migration Cost enquiry and enumerates the specific properties included (key, label, type, required, help text, allowed options). It clearly distinguishes itself from submit_enquiry by the closing instruction, though it does not explicitly contrast with enquiry_describe.

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 description explains that answers should be passed to submit_enquiry keyed by field key, establishing a clear downstream usage context for the tool. It does not explicitly state when not to use this tool or compare against enquiry_describe, so it falls just short of a 5.

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?

With no annotations, the description carries the full burden, and it discloses the two-step validation flow, the exact consent line, the email with a click-required link, and the fact that providers see the enquiry only after the click. The only undisclosed traits are confirmation-token expiry and step-2 return/error behavior, which are not critical to invoking the tool correctly.

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?

The description is long but dense: every sentence covers a distinct, load-bearing fact (scope, step 1, step 2, consent, email link), and the 'Step 1:'/'Step 2:' markers make it scannable. It is front-loaded with the most important scoping information — not a purchase.

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 complex two-step tool with no output schema and no annotations, the description covers the return content of step 1 (summary, consent line, token), the submission side effect, and the email notification. The remaining gaps — step 2's return value and validation-failure behavior — are minor relative to everything an agent must know to run the flow.

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?

The schema already covers all three parameters (100% coverage), including the full consent text and the confirmation-token origin, so the baseline is 3. The description adds workflow meaning beyond the schema: answers are keyed by the sibling tool's field keys, both calls must send identical answers, and the confirmation token is only used in step 2 after explicit approval.

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 states a specific verb and resource ('Submits an enquiry to M365 Migration Cost') and immediately scopes it with 'NOT a purchase, NOT a guaranteed quote.' The two-step submission workflow and the reference to 'field key from enquiry_fields' differentiate it from the sibling tools, which describe fields rather than submit.

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 description gives explicit workflow conditions: call first with consent=true to validate, then 'only if the person agrees, call again' with the confirmation token. It routes the agent to enquiry_fields for field keys but never states an explicit when-not-to-use rule for siblings; the 'not a purchase' framing is a scoping cue rather than a full alternative comparison.

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