Sandwich Public Care Directory

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

Annotations already declare the tool as read-only, idempotent, and non-destructive. The description adds context about the dataset and input factors but does not disclose output format, units, or edge cases. It does not contradict the annotations, but it adds only limited behavioral detail beyond what the 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?

The description is one concise sentence, front-loaded with the action ('Estimate'). Every word contributes to explaining the purpose and data source, with no redundancy or 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?

The description covers inputs and data source, and the annotations provide safety context. However, with no output schema, it does not specify what the estimate returns (e.g., total cost, annual cost, currency), which is a notable gap for a calculation tool. It is reasonably complete but not fully self-contained.

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 each parameter already has a clear description. The tool description restates the inputs (state, care type, years, inflation) but does not add new semantic meaning or usage details beyond the schema. Baseline 3 is appropriate given the high schema coverage.

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 ('estimate') and a clear resource ('long-term care cost') while naming key inputs (state, care type, years, annual inflation) and the data source (Sandwich's CareScout 2025 dataset). This clearly distinguishes it from sibling tools like get_channel or search_care_resources, 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?

The description does not state when to use this tool versus alternatives. It only describes what it does; there is no mention of when to prefer this over search_care_resources or other tools. Usage is implied by the function name but not explicitly guided.

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, idempotentHint, and destructiveHint, covering the safety profile. The description adds value by specifying that only public channels are supported and that the return includes metadata and canonical links, which are behavioral details not present in 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, compact sentence that is front-loaded with the action and resource. Every word earns its place; there is no redundancy or 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 simple read tool with one well-documented parameter and no output schema, the description sufficiently states what is returned (metadata and canonical links) and the constraint (public, by slug). It covers the essential purpose without needing to enumerate return fields.

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 'slug' parameter is well-described with concrete examples. The description itself does not add any parameter meaning beyond what the schema already provides, so a 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 uses a specific verb ('Return') and names the exact resource ('metadata and canonical links for one public Sandwich channel by slug'). It clearly distinguishes this tool from siblings like calculate_long_term_care_cost and search_care_resources, which are not channel-focused.

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 retrieving a single channel when you already know its slug, which is clear context. However, it does not explicitly state when not to use it or mention alternatives, so it stops short of full usage 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds the useful behavioral constraint that it searches only 'public' resources, but does not describe result format, ordering, or pagination. 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 a single, well-structured sentence that front-loads the verb 'search' and immediately specifies the resource scope. Every word adds value, with no fluff or 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 moderately simple search tool with two well-documented parameters and strong annotations, the description adequately covers the content types searched. It lacks explicit mention of result format, but the absence of an output schema and the presence of a limit parameter make the behavior reasonably clear. The scope of 'public' resources is also a useful contextual detail.

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%: both 'query' and 'limit' have descriptive text with examples and constraints. The tool description does not need to add parameter details; the schema fully documents them, so 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 states the tool 'search' across a specific set of public resource types (channels, guides, reports, answers, glossary terms, tools) for a defined topic (aging-parent and sandwich-generation care planning). This specific verb+resource+scope distinguishes it from sibling tools like calculate_long_term_care_cost and get_channel.

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?

It provides clear context that this is a broad search tool for public care-planning resources, implying when to use it (when you need to find relevant information) versus more specific tools. However, it does not explicitly mention alternatives or when not to use this tool.

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