site

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

With no annotations, the description discloses the primary return behavior but stays silent on side effects, state progression, invalid choice handling, or permissions. Some transparency is present, but the absence of annotations leaves gaps.

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 sentence, front-loaded with the input contract and output alternatives. No wasted words, though the title and description overlap slightly.

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 core call contract is present, but an agent is left to infer the workflow (how to obtain the question id, how to use the returned next question, what a verdict looks like) and there is no output schema to fill gaps.

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 provides only names/types (question string, choice integer). The description adds 'question id' and 'choice index', clarifying that question is an identifier and choice is an option index, but does not explain valid ranges, format of ids, or how to obtain them.

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 behavior: takes a question id and a choice index, returns the next question or final verdict. It is distinct enough from the sibling checker tools, though it never names them.

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?

Usage is implied from the flow ('answer a question to get next step'), but there is no explicit when-to-use vs checker_start/checker_tree or note that it should be called after a question is obtained.

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. It only identifies the tool as the first question of a decision guide, but does not explain what happens when it is called, what output or response to expect, whether it starts a stateful session, or any side effects. This is severely insufficient.

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 its single sentence is largely redundant with the title and does not earn its place by adding meaningful information. It is under-specified rather than efficiently concise.

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?

There is no output schema and no annotations, so the description must compensate by explaining what the agent receives after invocation and how this step fits into the overall decision guide flow. It only identifies the tool as the 'first question', leaving the agent without enough context to use the result or proceed 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 and an empty input schema, so no parameter documentation is needed. The schema fully communicates that no arguments are required, and the description adds nothing about parameters, which is acceptable in this case.

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 'The first question of the Which mail merge to PDF route? decision guide' essentially restates the title 'Start: Which mail merge to PDF route?' with only the minor additions of 'first question' and 'decision guide'. There is no concrete verb describing what the tool does when invoked, so it borders on tautology.

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 no guidance on when to call this tool versus its sibling tools such as checker_answer, checker_tree, or submit_enquiry. There is no mention of alternatives, conditions, or sequencing, leaving the agent to infer that it should be used to start the guide.

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. It inventories the content scope (every question, option, verdict) but says nothing about return format, tree structure, ordering, or whether any information is excluded. An agent knows what content domain to expect, not what the tool actually returns.

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?

A single 20-word sentence that front-loads the content inventory and closes with the purpose. Minor redundancy: 'Every question, option and verdict' largely restates the title 'The whole decision tree', but the added guide name prevents it from being purely tautological.

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 content tool, the description is adequate: it names the content source and its purpose. However, with no output schema, it leaves the return representation (structured tree? flat list? JSON?) and the shape of the 'verdicts' unstated, which an agent would need to predict the result reliably.

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 trivially covers 100% and the baseline of 4 applies. The description correctly adds no parameter-related noise because there is nothing 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 resource precisely: 'Every question, option and verdict of the Which mail merge to PDF route? guide', which clearly distinguishes it from the sibling checker_answer/checker_start tools (the full tree vs. individual steps). It lacks an explicit verb stating what the tool does with the tree — retrieve it? render it? — but the intent is evident from the naming and phrasing.

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?

'For reasoning end to end' is an implied usage signal — this tool is for traversing the whole guide rather than fetching one answer — but it never names alternatives or states when checker_answer, checker_start, or the enquiry_* tools should be used instead. The guidance is suggestive, not 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 and does so well: it discloses that nothing is bought, ordered, or paid, that no quote is guaranteed, that it is free, and exactly what the call returns—recipients, consent wording, and confirmation method. This gives an agent clear behavioral expectations beyond the tool 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, front-loaded with 'Read first' and the core purpose, and every clause adds either scope, disclaimers, or return contents. There is no filler, schema repetition, or unnecessary detail.

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-input, no-output-schema explainer, the description is complete: it says what the tool does, what it is not, and what its response contains. An agent can confidently decide when to call it and what to expect.

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 has zero parameters, so there is no parameter documentation burden; the baseline for a zero-parameter tool is 4. The description adds no parameter meaning, but none is needed.

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 ('States plainly') and resource ('what submit_enquiry does on Mail Merge PDF'), making it clear this is an explanatory tool rather than the submit action itself. It differentiates itself from the sibling submit_enquiry by pointing to that action as its subject, and the title reinforces the scope.

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' is a direct usage cue to invoke this tool before submitting an enquiry, and the description frames it as the plain-language explainer preceding submit_enquiry. It does not explicitly mention alternatives or when not to use it, so it stops short of full routing 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?

With no annotations provided, the description carries full responsibility. It indicates a read-only retrieval of field definitions and enumerates the content, which is transparent enough for a parameterless lookup. It does not disclose the exact return format or error behavior, though those gaps are minor given the tool's simplicity.

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, efficient sentence that front-loads the resource and enumerates the returned attributes before adding a usage hint. There is no filler or repetition, though it could be marginally improved by starting with an explicit verb.

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 parameterless tool with no annotations and no output schema, the description is largely complete: it explains what is returned, which attributes are included, and how to use the result with submit_enquiry. The main missing detail is the exact return container (list vs. object), but this is a reasonable gap for such a simple retrieval 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 takes zero parameters, so the description has nothing to add beyond the empty schema. The baseline for a 0-parameter tool is 4, and the description's mention of field keys aligns with the downstream submit_enquiry flow, adding slight contextual value.

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 Mail Merge PDF enquiry') and enumerates the attributes it exposes (key, label, type, required, help text, allowed options). The verb is implicit rather than explicit, but the scope is unambiguous. It makes a partial distinction from submit_enquiry, though not from the other sibling tools.

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 an implied usage context: fetch fields first, then pass answers to submit_enquiry keyed by field key. However, it does not explicitly state when to use this tool over enquiry_describe or the checker tools, nor does it mention any exclusions or prerequisites. The guidance is inferable but not 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 provided, the description carries the full burden and delivers extensively: it discloses that this is not a purchase or guaranteed quote, that a second call is required for actual submission, that the person receives an email link that must be clicked before any provider sees the enquiry, and it prints the exact consent line the person must agree to.

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 every sentence earns its place given the two-step, consent-bearing, email-verification flow. Purpose and exclusions are front-loaded in the first sentence, and the protocol is sequenced clearly. The consent line is repeated from the schema, but the repetition is functional since the agent must relay it verbatim to the person.

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 high-complexity tool with no annotations and no output schema, the description is remarkably complete: step 1's return values (summary, consent line, confirmation token), step 2's conditional and effect (submission plus email link requirement) are all specified. Nothing an agent needs to invoke the tool 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 description coverage is 100%, setting a baseline of 3. The description adds real meaning beyond the schema: answers are keyed by field key from enquiry_fields, the confirmation parameter is tied to step 1's returned token, and consent is contextualized as 'true only when the person has agreed' to the quoted line. This cross-tool and cross-step context exceeds the schema alone.

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 ('Submits an enquiry to Mail Merge PDF') and reinforces scope with exclusions ('NOT a purchase, NOT a guaranteed quote'). The title and description together clearly distinguish this from the checker_* and enquiry_* siblings, which serve different phases.

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?

Provides an explicit two-step call protocol with sequencing: step 1 validates and returns a token, step 2 submits only after the person agrees. It names enquiry_fields as the source of field keys, giving the agent routing context. It does not explicitly contrast with sibling tools, but the conditional 'only if the person agrees' is strong usage guidance.

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