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

The description goes beyond the readOnlyHint annotation by disclosing that the tool always refuses, explains why (reCAPTCHA), and what it provides (explanation and link). This is a behavioral trait that is not obvious from annotations alone and is essential for the agent to set correct expectations. No contradiction with the readOnlyHint.

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 two sentences, front-loaded with the most critical fact (not automatable, always refuses). It is concise with zero fluff. Every sentence earns its place: the first states the refusal, the second tells the agent what to use it for.

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 tool whose sole purpose is to refuse and redirect to a browser, the description covers what the agent needs to know: the outcome (refusal), the reason (reCAPTCHA), and the output (explanation and link). No output schema exists, so the description implicitly covers what is returned. The description is complete for an agent to decide whether and how to call it.

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 only 50% (only the 'link' parameter has a description; 'option_ids' is undocumented). The description does not mention parameters at all, so it fails to compensate for the gap. For the 'link' parameter, the schema description is detailed, but the description adds no value beyond that. The 'option_ids' parameter remains unexplained, and the description provides no clues about its purpose.

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 very specific behavior: the tool always refuses approval, provides an explanation, and returns a link for browser use. This clearly distinguishes it from siblings like housecallpro_decline_estimate or housecallpro_get_estimate, which perform different actions. The verb 'refuses' and the resource 'estimate' are explicit.

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 tells the agent to use this tool to get the explanation and link for browser approval, implying it is not for actual approval. It does not explicitly state when not to use it or mention alternatives, but the context (non-automatable, always refuses) makes the intended usage clear. A small gap: it doesn't say 'use housecallpro_get_estimate for reading estimates' or similar, but the purpose 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?

Annotations include destructiveHint=true, but the description goes further by stating 'it cannot be undone from here' and explaining the confirmation mechanism in detail: a native confirmation prompt when supported, otherwise a two-step flow where the first call posts nothing and returns a preview and confirmToken. This transparently discloses the side effects and the fallback behavior. No contradiction with annotations.

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 composed of three well-focused sentences: the operation, the confirmation flow, and the irreversible consequence. It is front-loaded with the purpose and every sentence earns its place, including the important cross-reference to MCP_CONFIRM_MODE for the fallback path.

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 destructive tool with a two-step confirmation fallback, the description covers both execution paths and explains what the first call returns (preview and confirmToken). It does not explicitly state what the final call returns or describe the success response, but given the protocol reference and the detail in the schema, it is sufficiently complete for an agent to invoke 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 input schema already documents all three parameters with full descriptions at 100% coverage, including the nuanced confirmToken usage. The description adds no additional parameter-level semantics, so the baseline score of 3 is appropriate; it does not need to compensate for schema gaps.

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 exact operation ('Decline one or more options on an estimate') and clarifies the semantic outcome ('Declining tells the contractor you are not proceeding'). This clearly differentiates it from the sibling housecallpro_approve_estimate, which performs the opposite action.

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 conveys when the tool is appropriate: when the user wants to decline an estimate option and does not intend to proceed. It also warns that the action cannot be undone, which is critical usage guidance. It does not explicitly name alternatives or exclusion conditions, but the purpose and consequence make the intended use obvious.

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?

Annotations already declare readOnlyHint=true, so no read-only disclosure is needed. The description adds useful context with the returned fields and input source, but does not go into behavior such as missing-company handling, errors, or response shape.

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 short sentences with no redundant wording. The action and key return fields are front-loaded, and the input instruction is a single clear follow-up.

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 one-parameter, read-only lookup, the description is complete: it specifies the input origin, the output fields, and the purpose. No output schema or nested-object complexity means there is little additional context an agent needs.

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 already states the organization_id is an Organization UUID from an estimate. The description's 'Takes the organization_id from an estimate' essentially repeats that, so it adds little beyond the 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 uses a specific verb ('Look up') and a concrete resource (the contractor/company behind an estimate), and names the exact data returned. It is clearly differentiated from sibling tools like housecallpro_get_estimate because it targets the company rather than the estimate 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 description establishes the triggering context: use it when you have an estimate and need contractor details, taking organization_id from that estimate. It does not explicitly state when not to use it or compare with alternatives, so it stops 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?

Annotations already mark readOnlyHint=true, so the safety profile is covered. The description adds valuable behavioral detail: the compact view returns both cents and dollars, the raw view returns upstream document with cents only, and it notes the raw size (~4.8 KB). This goes beyond the annotation without contradicting it.

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 two sentences, with the primary purpose and content front-loaded in the first sentence and the view options compactly explained in the second. No wasted words or redundant phrases.

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 must convey the return shape. It does so thoroughly for both compact and raw views, including the money format difference. Minor omissions like error handling or not-found behavior are acceptable given the read-only nature and schema coverage.

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%, so both link and view are already well documented. The description reiterates the view behavior (compact vs raw) and money representation, but does not add new meaning beyond the schema. Per guidelines, baseline 3 is appropriate when schema does the heavy lifting.

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 ('Read') and resource ('an estimate') and enumerates the contained data (line items, totals, tax, company, approval state). It clearly distinguishes from sibling tools like get_invoice (invoices) and approve/decline (actions) by focusing on read-only retrieval of estimates.

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 implies usage ('Read an estimate a contractor sent you') but does not explicitly contrast with alternatives like approve_estimate or decline_estimate, nor state when not to use it. The parameter guidance about omitting link when exactly one is configured is present, but tool-level usage guidance is implicit 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?

Beyond the readOnlyHint annotation, the description discloses that the document has no line items and that the portal shows a summary only. It also explains the compact/raw view difference, which is useful behavioral context for a read-only operation.

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: purpose first, then key output conventions, then an important caveat. Every sentence earns its place and there is no filler.

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 read-only tool with two well-documented parameters, the description plus schema cover input, output shape, and caveats. The lack of an output schema is compensated by the description's clear statement of what the tool returns.

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 link and view parameters are already fully described in the input schema. The description reinforces the view behavior and defaults but adds little semantic value beyond what the schema provides.

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: 'Read an invoice a Housecall Pro contractor sent you' and enumerates the returned data (amount, subtotal, tax, amount still owed, payability). The resource is unambiguous against sibling tools like get_estimate because it explicitly targets invoices.

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 clear usage context: use it when you need the summary of an invoice sent by a Housecall Pro contractor. It does not explicitly discuss exclusions or alternatives, but the distinction from estimate-focused siblings is evident.

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?

Annotations already establish readOnlyHint and openWorldHint, so the bar is lower. The description adds useful behavioral context by explaining that the tool performs a live connectivity check against an external service and validates a customer link, without suggesting destructive 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?

Two sentences with no filler. The first sentence states the core purpose, and the second provides actionable usage guidance. Every word 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?

For a zero-parameter healthcheck tool, the description covers what it checks and when to run it. It does not describe the return format, but the tool's simplicity and the absence of required inputs keep this gap minor.

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 no parameters and schema description coverage is 100%, so there is nothing for the description to clarify. The baseline of 4 applies because no parameter ambiguity exists.

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 a specific verb and resource: it checks server reachability to Housecall Pro and whether a configured customer link resolves. This clearly distinguishes the healthcheck from sibling data-fetching and mutation 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 explicitly says 'Run this first when a tool fails,' giving clear when-to-use guidance in a diagnostic workflow. It does not name alternatives or state when not to use it, but the context is strong enough for an agent to route correctly.

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?

Beyond the readOnlyHint annotation, the description discloses a critical boundary: 'retrieval tokens are credentials and are never returned.' It also clarifies that only 'labels and document kinds' are exposed, giving the agent a concrete expectation of what the response will and will not contain. This materially reduces the risk of misuse.

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 two sentences with no filler. The first sentence front-loads the core purpose and scope; the second sentence adds a valuable security-relevant constraint. Every word 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?

For a parameterless, read-only list tool with no output schema, the description fully equips the agent: it states what is listed, what the output consists of, and what will never be returned. No missing information is needed to call 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 and the schema coverage is effectively complete, so there is nothing to document. The description's focus on output scope rather than inputs is appropriate for a parameterless tool, meeting the baseline for 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 a specific verb ('List'), a specific resource ('Housecall Pro customer links'), and a precise scope ('this server is configured with'). It is clearly distinct from sibling tools, which target estimates, invoices, company info, or health checks, so an agent can differentiate it 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?

The description makes the usage context clear: call this tool when you need to see which Housecall Pro customer links are configured. It does not explicitly name an alternative or state when not to use it, but none of the siblings perform link listing, so the guidance is sufficient for correct selection.

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