site

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 provides none: no indication of whether this is a read operation, what output or side effects occur, what 'compared comparison' means, or what the tool actually does when invoked. The description adds no behavioral transparency beyond the name.

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 but not well-structured: 'compared comparison' is redundant and confusing. The intended meaning is not front-loaded, and the awkward phrasing weakens what little clarity exists.

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?

The tool has no output schema and no annotations, and the description leaves critical information undefined: what 'Six routes to a completed conveyance' refers to, what kind of comparison is performed, what the result looks like, and how this differs from the sibling compare tools. An agent cannot confidently select or invoke this tool based on the provided definition.

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 description coverage is 100%, so there is no parameter documentation burden. The description references 'criteria and any filters' as conceptual content, but since no input schema exists, no parameter explanation is required.

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 is essentially a tautology of the tool name: compare_criteria is described as 'criteria ... compared comparison.' It identifies the subject matter (criteria and filters of the Six routes to a completed conveyance), but fails to state a clear action such as 'compare', 'view', or 'return' and does not distinguish what this tool does versus the sibling tools compare_options or compare_table.

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?

There is no guidance on when to use compare_criteria versus compare_options, compare_table, or the enquiry_* siblings. No context, conditions, or exclusions are provided, so an agent cannot determine the appropriate selection among the listed siblings.

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 behavioral burden. It discloses one trait: results can be optionally filtered by a tag value. But it does not indicate whether the operation is read-only, what the comparison output looks like, whether there are pagination or limit behaviors, or what happens when no filter is provided.

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, but the brevity comes at the cost of clarity: the phrase 'compared comparison' is redundant and the sentence lacks a clear front-loaded action. The filter behavior is buried at the end after a long noun phrase, making the structure harder to parse.

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 simple tool with two optional parameters this could be adequate, but the 0% schema coverage, absence of annotations, and missing output schema leave too much undefined. An agent still has to infer the meaning of filterKey and the exact return value, so the description is not complete enough for reliable invocation.

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 0% and both properties are bare strings with no enums or descriptions. The description partially explains that filtering is 'by a tag value,' hinting at filterValue, but it never clarifies filterKey, how the two parameters interact, or what valid values look like.

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 resource ('options in the Six routes to a completed conveyance') and the compared attributes (name, best for, tags), so an agent can roughly infer a comparison tool. However, it lacks a clean verb—'compared comparison' is ungrammatical and redundant—and the title 'The options' adds no action or differentiation.

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?

There is no guidance on when to use compare_options rather than sibling tools like compare_criteria, compare_table, or the enquiry tools. The only usage hint is the optional tag filter, which is a parameter behavior rather than a routing rule.

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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It describes what the table contains but does not say whether it returns, displays, or exports the table, nor does it mention how the optional 'option' parameter affects the result or whether the operation is read-only.

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, but the phrasing 'compared comparison' is redundant and the noun phrase 'Six routes to a completed conveyance' is awkward. It conveys the essential idea without much waste, but the structure is not as clean or front-loaded as it could be.

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 simple table-query tool, the description gives a basic sense of the output, but with no output schema and no annotations it should clarify how the table is organized and what the 'Six routes' are. The optional filtering behavior is covered by the parameter schema, so this is not severely incomplete, just somewhat thin.

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 100%, and the schema already explains that 'option' is 'one option's name, else all.' The description adds no further parameter-level meaning, so the baseline score of 3 is appropriate.

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 comparison table and states its content: each option's value on every criterion. It is reasonably clear, but it lacks a direct verb and does not explicitly differentiate compare_table from the sibling tools compare_criteria and compare_options beyond the phrase 'the full table.'

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?

No guidance is given about when to use this tool versus compare_criteria or compare_options. The phrase 'the full table' implies a comprehensive view, but there are no explicit conditions, alternatives, or exclusions to help an agent choose it confidently.

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 behavioral burden and largely meets it: it clarifies that the underlying process has no purchase/payment, is free, and has no guaranteed quote, and it says the tool itself 'returns' explanatory content. It does not explicitly state that invoking this tool is side-effect-free, but the descriptive framing makes that clear.

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 most important usage note ('Read first') and then delivers the key behavioral facts in compact sentences. It repeats some of the title's caveats, but the repetition is minor and does not bloat the text.

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 explainer tool with no output schema, the description tells the agent what the tool does, what the user experience will be, and what the return content covers ('who receives the details, the consent wording, and how the person confirms'). Nothing essential is missing for correct invocation.

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 input schema is empty with zero parameters, so there are no parameter semantics for the description to add. The baseline of 4 applies because there is nothing for the tool to compensate.

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 exact resource it explains — submit_enquiry on Compare My Conveyancing — and states the action with a specific verb ('States plainly what... does'). It also distinguishes itself from the transactional sibling by emphasizing that nothing is bought, ordered, or paid.

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 opening 'Read first' is an explicit directive to use this tool before acting on an enquiry, giving clear context. It does not enumerate sibling alternatives or state when-not-to-use cases, but the prerequisite framing is unambiguous.

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 provided, the description carries the transparency burden and handles it well by enumerating exactly what information the tool exposes: keys, labels, types, required flags, help text, and conditional options. It does not promise behavior beyond this, avoiding misleading claims for a simple field-listing tool.

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 concise sentences: the first front-loads the resource and its full returned content, and the second gives the actionable relationship to submit_enquiry. Every word contributes, with no vague filler or repetition of the title.

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 no-parameter, no-output-schema tool, the description is effectively complete. It specifies the domain, the fields returned, the conditional nature of options, and how the output should be consumed by submit_enquiry. An agent has enough information to select and interpret the tool correctly.

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, so the baseline is 4. The description correctly focuses on the returned field metadata rather than input semantics, and the note about passing answers keyed by field key clarifies how the results should be used.

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 clearly identifies the resource ('Every field of the Compare My Conveyancing enquiry') and the specific metadata returned: key, label, type, required status, help text, and allowed options. It also ties the tool to its intended consumer, submit_enquiry, which distinguishes it from sibling tools like compare_criteria or 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 gives a clear usage context: retrieve the fields to learn how to structure answers for submit_enquiry, with keys used as the linking mechanism. It does not explicitly list when to avoid this tool in favor of siblings, but the connection to submit_enquiry provides enough practical guidance.

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?

No annotations exist, so the description carries the full burden and discharges it: it discloses the two-phase validate/submit flow, that step 1 returns a summary and consent line to be shown to the person, that submission triggers a confirmation email whose link must be clicked before any provider sees the data, and the exact consent semantics. This is substantially more than the schema conveys.

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-loads the critical distinction (not a purchase) and then walks the two steps in order. It is on the long side and the consent text is duplicated verbatim from the schema, but every clause serves the two-step protocol or the consent requirement.

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, the description explains what each step returns (summary, consent line, confirmation token; then a confirmation email link), what the person must do, and when providers gain visibility. Nothing an agent needs to call this correctly 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 the baseline is 3, but the description adds sequencing semantics the schema cannot express — that consent must reflect genuine agreement and that the token from step 1 is required for step 2 despite being optional in the schema. That meaningfully clarifies invocation beyond the field descriptions.

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+resource ('Submits an enquiry to Compare My Conveyancing') and immediately disambiguates scope with 'NOT a purchase, NOT a guaranteed quote.' An agent can distinguish this from the compare_* siblings without opening any schema.

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?

Gives an explicit two-step protocol: Step 1 with answers+consent=true to validate and get a token; Step 2 only if the person agrees, repeating answers plus the confirmation token. Both when-to-call conditions and the gating on human approval are stated, not implied.

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