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 meaningful work: it discloses that nothing is bought, ordered or paid, that no quote is guaranteed, and that the enquiry is free. It also previews the returned content (recipients, consent wording, confirmation). It does not cover possible failure or timing behavior, but for a read-only informational tool the disclosure is solid.

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 and front-loads the actionable cue ('Read first') and the core content, with the returned items listed last. There is mild redundancy in 'Nothing is bought, ordered or paid,' but overall it stays lean and earns its length.

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?

With no output schema and no annotations, the description must supply both the return content and the behavioral context, and it does: it enumerates the returned items and states the key constraints of the enquiry flow. Given the tool is a zero-parameter informational resource, this is adequately complete.

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 takes zero parameters, so there is no parameter semantics to explain and the baseline of 4 applies. Nothing is misrepresented or missing in this dimension.

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 the specific verb+resource: it 'states plainly what submit_enquiry does' and returns who receives details, the consent wording, and the confirmation step. By naming the sibling submit_enquiry and clarifying it is the descriptive counterpart, it helps distinguish itself. It is slightly indirect in framing its own purpose through the sibling, but an agent can tell what it returns.

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?

'Read first' provides an ordering cue that this should be consulted before the enquiry flow, and naming submit_enquiry implies the sequencing relative to that sibling. However, there is no explicit when-not or explicit comparison against enquiry_fields, so usage is implied rather than spelled out.

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 and no output schema, the description carries the full burden, and it does disclose the returned shape: key, label, type, required, help text, and allowed options where present. It does not state auth requirements or whether the field list is static or configurable, but for a zero-param read that is a minor gap.

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 sentences, both earning their place: the first defines the payload contents, the second defines how to consume it. The most important information (what this returns and how it connects to submission) is front-loaded.

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-param introspection tool with no output schema, describing the returned field attributes is exactly the right content, and the linkage to submit_enquiry closes the loop. Slightly incomplete in that it never clarifies its relationship to enquiry_describe or whether the field set is per-form.

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 takes zero parameters, so the baseline of 4 applies. No parameter semantics exist to document beyond the implicit contract that field keys returned here are the keys expected by submit_enquiry.

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 names the resource precisely (the fields of the Web design Suffolk enquiry) and enumerates what each field record contains (key, label, type, required flag, help text, allowed options). An agent can tell it is a schema/introspection read rather than a submission, though the verb is implied rather than stated. It is distinguishable from submit_enquiry but not explicitly from 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?

It gives concrete workflow guidance: 'Pass answers to submit_enquiry keyed by field key,' which tells the agent this tool precedes submission and supplies the keys. No exclusion or boundary is drawn against the sibling enquiry_describe, so the when-not case is left implicit.

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 largely succeeds: it explains that step 1 returns a summary, consent line, and token; step 2 submits and triggers an email with a link that must be clicked before providers see it. It also defines what 'consent' means. It does not mention rate limits, error behavior, or whether the token expires, but for a two-step form submission this is strong.

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 front-loaded with the purpose and the critical 'NOT a purchase' warning, then proceeds through the two steps efficiently. The consent sentence is a direct quote, which is necessary for legal clarity, though slightly verbose. Overall, every sentence earns its place.

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?

Given the complexity (two-step flow, nested answers object, consent gate, email confirmation), the description covers the essential mechanics an agent needs to call the tool correctly across multiple turns. It lacks detail on token expiry or error handling, but with no output schema, the return values (summary, consent line, token) are well explained.

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 the schema documents each parameter. The description adds crucial step-level semantics: which parameters belong to step 1 vs step 2, and that the confirmation token comes from step 1 after approval. This exceeds the baseline for a high-coverage 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?

The description states a specific verb+resource ('Submits an enquiry to Web design Suffolk') and immediately distinguishes it from a purchase or guaranteed quote. It also names the sibling tools implicitly by referencing 'enquiry_fields', making it clear how this tool relates to the others.

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?

It provides an explicit two-step workflow: step 1 validates and returns a summary and token; step 2 submits only after the person agrees. This is the rarest form of usage guidance—it tells the agent exactly when and how to invoke the tool across turns, and when not to (not a purchase).

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