GeezerKeeper Referral Exit Routes

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

Annotations declare readOnlyHint=true, destructiveHint=false, indicating a safe read operation. The description adds behavioral context beyond annotations by stating that no personal information is accepted, which is a constraint not captured in structured fields. No contradictions.

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?

Single sentence, front-loaded with the action and options, zero waste. 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?

Given only 2 parameters, no output schema, and annotations covering safety, the description is nearly complete. It briefly explains the choice logic. A minor gap is no mention of return value, but overall sufficient.

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% with both parameters well-documented in the input schema. The description mentions 'recipient count and intended use' aligning with the params, but adds no further detail beyond the schema. Baseline 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 clearly specifies the verb 'choose' and the resource 'GeezerKeeper workflow', listing the three options (free, $19 consumer, $59 professional) and the criteria (recipient count, intended use). This distinguishes it from sibling 'get_*' 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 indicates when to use the tool ('using only recipient count and intended use') and states a constraint ('No personal information is accepted'). It does not explicitly state when not to use it or list alternatives, but the sibling tools are all retrieval-focused, making the usage context 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?

Annotations already declare readOnly, idempotent, and non-destructive hints. The description adds valuable context about the returned data (identity, contact, pricing, privacy-boundary info) beyond annotations, but does not disclose any additional behavioral traits beyond what annotations imply.

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, well-structured sentence that front-loads the key information. No extraneous words; every part contributes to understanding the tool's purpose.

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 tool's simplicity (no parameters, no output schema), the description is complete. It clearly specifies what the tool returns and that it requires no input, leaving no gaps for an agent to misunderstand.

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?

There are no parameters, so schema coverage is 100%. The description explicitly states 'Accepts no inputs,' which is sufficient. Baseline for zero parameters is 4.

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 states the tool returns canonical public business identity, contact, pricing, and privacy-boundary information. It distinguishes itself from sibling tools like get_location and get_services by being a general-purpose info tool. The verb 'Return' and resource specification are precise.

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 the tool is for getting public business info, but it does not explicitly state when to use it versus alternatives (e.g., get_location for location, get_services for services). No when-not conditions are provided.

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 the tool read-only and non-destructive. The description adds beyond this by specifying that the tool 'do[es] not expos[e] a private street address' and 'do[es] not accept[t] a location input,' providing additional behavioral context that is not captured by 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 a single, well-structured sentence no longer than necessary. It front-loads the key action ('Return online delivery and U.S. service coverage') and efficiently conveys the tool's constraints without any extraneous words.

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 absence of an output schema, the description should ideally describe the return structure. It only mentions 'online delivery and U.S. service coverage' without specifying the format (e.g., list, object), leaving ambiguity for an agent. With no parameters and safe annotations, this is a moderate gap.

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 parameters with 100% coverage, so the schema fully documents parameter absence. The description adds meaning by explaining why there are no parameters ('without accepting a location input'), clarifying the tool's purpose and reinforcing 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 clearly states the tool 'Return[s] online delivery and U.S. service coverage,' using a specific verb and resource. It also distinguishes itself by noting it does 'not exposing a private street address or accepting a location input,' which differentiates it from potential sibling tools that may accept location parameters.

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 implicitly suggests use for obtaining coverage information but does not explicitly guide when to use versus alternatives. It lacks explicit 'when not to use' statements or mentions of sibling tools like 'get_services' or 'lookup_exit_route' that might offer related functionality.

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 and destructiveHint=false, indicating safe reading. The description adds behavioral context by specifying that the category parameter is safe (cannot carry personal info), which is beyond what annotations provide.

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. Every word adds value: the first sentence states purpose, the second adds parameter guidance. Front-loaded and efficient.

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 one optional parameter and no output schema, the description fully covers what the tool returns (three pricing tiers) and the parameter's safety and enumeration. No 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 already describes the category parameter with enum values. The description adds value by clarifying that the parameter is safe and cannot carry personal information, reinforcing privacy considerations.

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 states it returns current services and prices with specific tiers ($0, $19, $59), using a strong verb ('Return'). It distinguishes from sibling tools like get_info or get_location by focusing on service pricing.

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 mentions the category parameter is enumerated and cannot carry personal information, offering some guidance. However, it does not specify when to use this tool vs alternatives (e.g., when to choose get_info instead).

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?

The description reveals that the server accepts no personal fields and never sends the request, which adds behavioral context beyond the annotations (readOnlyHint, destructiveHint, idempotentHint). It also instructs to replace placeholders locally, enhancing transparency.

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 concise with two sentences, front-loading the core action and purpose. Every sentence adds value, with no wasted words.

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 with no output schema, the description covers the essential: template nature, unfilled state, target recipients, and key behavioral notes. Missing details like error handling or format are acceptable for this 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?

With 50% schema description coverage, the description does not add significant meaning beyond the schema. It briefly echoes the schema's description for sourceId but does not explain recipientType or provide additional context for the parameters.

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 states the tool's purpose: returning an unfilled template for a referral network or identifiable provider. The verb 'return' and resource 'template' are specific, and the description distinguishes from sibling tools like choose_private_workflow or get_info.

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 context on usage (replace placeholders locally) but does not explicitly state when not to use this tool or mention alternatives. It implies usage for obtaining a template, but lacks explicit guidance on 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?

Annotations already declare readOnlyHint and idempotentHint, matching the read-only nature of the tool. Description adds value by noting the route is 'maintained' and warning about personal information, but no contradictions.

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, minimal and efficient. No wasted words. Front-loaded with the core action.

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 single-parameter lookup with good annotations, the description covers the purpose and constraints. However, lack of output schema means return format is only hinted at (stop-contact and privacy route).

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% and the parameter sourceId is fully described with an enum list. Description restates 'network identifier' but adds no new syntactic or semantic details 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?

Description clearly states the tool returns a 'maintained stop-contact and privacy route' for a senior-care referral network. It uses specific verb 'Return' and resource 'exit route', and distinguishes from sibling tools like get_info and get_services which serve different purposes.

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?

Description explicitly states 'never provide personal information' and that only a network identifier is required, giving clear usage guidance. However, it does not explicitly mention when not to use this tool or provide alternatives among siblings.

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