site

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 explaining behavior. It does not state whether this is a read operation, what the output looks like, what 'criteria and any filters' means operationally, or any edge cases. The description is a static noun phrase rather than a disclosure of 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?

The description is short and contains no fluff, which is good for conciseness. However, it is grammatically incomplete and reads awkwardly as 'The criteria ... comparison,' so the structure undercuts clarity even though the length is appropriate.

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 input parameters, no output schema, and no annotations, the description is the only source of context, and it only names the subject matter. It does not tell the agent what the tool returns, how the result is structured, or how it relates to compare_options and compare_table, leaving the tool incompletely specified for correct invocation and interpretation.

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 schema needs no parameter documentation and the description is not required to add parameter semantics. The baseline of 4 applies because there is simply nothing to compensate for.

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 as 'criteria and any filters' within 'Letting agent and property management systems used by UK agencies comparison', which hints at what the tool exposes. However, it is a noun phrase with no explicit verb, and it largely restates the title 'What is compared', so the purpose is only moderately clear.

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 about when to use compare_criteria versus its siblings compare_options, compare_table, or the enquiry_* tools. The agent must infer the tool's role purely from its name and the vague description, which is insufficient for confident selection.

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 behavioral burden. It usefully discloses that results include name, best-for, and tags, and that results can be filtered by a tag value. However, it does not state default behavior when no filter is provided, what filterKey means, or confirm the operation has no side effects.

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 a single sentence but with an awkward, overly long noun phrase: 'Letting agent and property management systems used by UK agencies comparison.' The main point is buried, and the lack of a lead verb makes it harder to parse. It could be more direct and 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?

With two undocumented parameters, no output schema, no annotations, and no differentiation from siblings, the description leaves too much to inference. Missing context includes the meaning of filterKey, the default result set, and the relationship to other comparison-related tools.

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 neither filterKey nor filterValue has any schema documentation. The description only mentions filtering by 'a tag value,' which likely maps to filterValue, but it leaves filterKey completely unexplained. This is insufficient compensation for the missing parameter metadata.

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 ('options' in the letting-agent comparison) and lists attributes (name, best-for, tags), which gives some clarity. However, it lacks an explicit verb such as 'list' or 'retrieve' and reads as a noun-phrase label rather than a complete tool instruction. It does not clearly distinguish itself from sibling tools like compare_table or compare_criteria.

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 about when to use compare_options versus its siblings. The phrase 'optionally filtered by a tag value' describes a filtering option within the tool, not a condition for choosing this tool over alternatives.

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 full burden of behavioral disclosure, but it only describes table content, not operation traits. It does not state that this is a safe read-only query, what happens with an invalid option value, or how the 'else all' default behaves. There is no contradiction with annotations since none exist.

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 compact sentence with the essential content ('each option's value on every criterion') front-loaded. The qualifier naming the comparison subject is verbose and the trailing '— the full table' is slightly redundant with the title, but there is no filler or schema repetition.

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 low-complexity tool with one optional, fully documented parameter and no output schema, the description is mostly adequate: an agent knows it will get the full option-by-criterion table. The notable gaps are the unstated relationship to the sibling compare tools and the absence of behavioral notes given zero annotations, but the risk of misusing this simple read-style tool is low.

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 documentation coverage is 100% — the schema already explains 'option' as 'one option's name, else all,' which is clear and sufficient. The description adds no parameter-level meaning on top of the schema, so the baseline of 3 applies.

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 tool's content precisely: each option's value on every criterion, i.e., the full cross-product comparison table. 'The full table' implicitly distinguishes it from the likely criterion-only and option-only sibling tools (compare_criteria, compare_options), though it never names them. It lacks an explicit verb like 'returns' or 'shows,' leaving the operation implied rather than stated.

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 explicit when-to-use guidance is given. The phrase 'the full table' hints that this tool is the comprehensive view versus the siblings, but it never tells the agent when to choose this over compare_criteria or compare_options, nor when a partial view would be more appropriate.

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. It transparently states that the tool 'states' and 'returns' information, and it clarifies that the underlying enquiry is free, not a purchase, and not a guaranteed quote. It does not explicitly state that calling enquiry_describe itself has no side effects, but the read-first framing and descriptive verbs make it unlikely to be misread as an action 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?

The description is compact and front-loaded with 'Read first,' followed by clear statements of purpose and return content. The title is long but contributes meaningful context. No sentence is wasted, though the title and description together are slightly repetitive.

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 tool with no output schema, the description adequately explains what the tool does, what it returns, and key facts about the subject it describes. It could more explicitly say 'use this before submitting an enquiry,' but the 'Read first' cue largely covers that need.

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 the schema is empty, so there is no parameter ambiguity to resolve. The baseline of 4 for zero-parameter tools applies, and the description sensibly adds no redundant parameter details.

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 uses the specific verb 'states plainly' and identifies the resource as 'what submit_enquiry does,' making it clear this is a documentation/explainer tool rather than an action tool. It is distinguishable from siblings like submit_enquiry and compare_options. However, the title 'What you get: an ENQUIRY with a human' is somewhat ambiguous and could be mistaken for the action itself, though the description immediately corrects this.

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 phrase 'Read first' provides a clear ordering cue, implying this should be consulted before using submit_enquiry. It does not explicitly name alternatives or state when not to use this tool, so guidance beyond sequencing is implied rather than explicit.

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 does state the output scope—every field, including options where present—and implies a read-only informational role, but it never explicitly says the call has no side effects or what the result structure looks like.

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 deliver a complete field inventory and a usage pointer with no filler. The description is front-loaded with the most important information and every clause adds value.

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 tool with no output schema, the description adequately explains what will be returned and how the results should be used. It does not mention sibling differentiation or explicitly confirm read-only behavior, but those are minor gaps for such a simple 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 input schema has zero properties and schema description coverage is 100%, so there are no parameters to document. The field-key mention is about downstream submit_enquiry usage, not this tool's parameters, so the zero-parameter baseline of 4 applies.

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—the enquiry field set—and enumerates its contents: key, label, type, required, help text, and allowed options. It stops short of an explicit verb like 'returns' or 'lists', and it does not explicitly distinguish itself from sibling enquiry_describe, so it is clear but not maximally distinct.

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 sentence 'Pass answers to submit_enquiry keyed by field key' gives concrete usage context: this tool should be used to discover field keys before submitting an enquiry. It does not state when to prefer this over the comparison siblings or enquiry_describe, but the downstream guidance is clear.

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?

There are no annotations, so the description carries the full behavioral disclosure burden. It reveals that step 1 only validates, step 2 actually submits, the person receives an email with a click link, and providers do not see the enquiry until that link is clicked. It also defines consent explicitly.

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 title front-loads the two-step and not-a-purchase framing. The description is dense but every sentence carries procedural information needed to invoke the tool safely. The repeated consent quote is justified because it defines a critical behavioral condition.

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 explains what step 1 returns, what the agent should show the person, what step 2 requires, and what happens after submission. An agent has sufficient information to execute both steps 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?

Schema coverage is 100%, so the baseline is 3. The description adds process-level meaning by tying answers to enquiry_fields keys, consent=true to explicit agreement, and the confirmation token to the step-1 result. Some wording duplicates the schema, but the two-call sequencing provides additional semantic clarity.

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: it submits an enquiry to Letting Agent Software, and explicitly contrasts itself with a purchase and a guaranteed quote. The two-step nature is made clear up front, which separates it from sibling tools like enquiry_fields and compare_options.

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 provides explicit step-by-step call guidance: first validate with answers and consent=true, then call again only if the person agrees, passing the confirmation token. It also says what the tool is not for, giving clear when-to-use and when-not-to-use guidance.

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