Checko — travel insurance guides and FAQ

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds modest value beyond them: the source site and the fact that content is Hebrew, plus that filtering is optional. No mention of result size, pagination, or freshness of the FAQ.

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 front-loaded sentence with the resource and its locale up front and the optional filter last; nothing wasted.

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-required-param, read-only lookup with fully documented schema and no output schema, the description is essentially sufficient — it states the return content (questions and answers) and the filter option. Only the exact shape of a returned entry is left unspecified, which is acceptable without an output schema.

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 single category parameter has an enum and its own description, so the schema does the heavy lifting. The description only restates that filtering by one category is optional, adding nothing about enum semantics or default behavior.

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?

Specific verb (Return) + resource (questions and answers from the checko.co.il FAQ) with a stated scope (Hebrew, optional category). It is clearly distinguishable from get_guide/list_guides by naming the FAQ resource, though it never explicitly contrasts 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?

'Optionally for one category' implies the filtering use case, and the read-only nature of the operation is evident from 'Return', but there is no explicit statement of when to reach for this versus get_guide or list_guides.

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, non-destructive and closed-world, so safety is covered. The description adds genuinely new context beyond that: the response is Markdown and the content is Hebrew, and only published guides are returned — material facts the annotations do not carry.

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 front-loaded sentence with no filler; the return format and language are surfaced before the identification detail. Every clause 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?

With no output schema and one enum parameter, the definition covers what an agent needs: format (Markdown), language (Hebrew), scope (published guides), and key (slug). It stops short of behaviour for unknown slugs, though the enum largely precludes that.

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%, but the single parameter is an enum listing all six valid slugs, which is self-documenting. The description only adds that the slug identifies a published guide; it adds little beyond the enum, but little 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?

States a specific verb ("Returns") and resource ("full Markdown text of one published guide") plus the lookup key. It implicitly separates itself from list_guides by saying "one", but it never names the siblings get_faq or list_guides, so differentiation is left to inference.

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 "one published guide, identified by its slug" implies the tool is for fetching content once a slug is known, but there is no explicit when-to-use guidance and no pointer to list_guides as the way to discover valid slugs. Usage is inferable but not stated.

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, non-destructive and closed-world, so the safety profile is fully covered. The description adds real context by naming the source site, the Hebrew language, and the returned fields (slug, title, URL), but says nothing about ordering, result caps, or what an empty result means.

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 front-loaded sentence that carries purpose, scope, return fields, and the optional filter with no filler. Nothing could be removed without losing information.

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 correctly enumerates the returned fields, which is exactly what an agent needs. The only shortfall is the absence of ordering/pagination expectations for a list endpoint, a minor gap for a small, closed-world guide index.

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 baseline would be 3, but the description adds substring-match semantics ("title contains a search term") where the schema only says "matched against guide titles". It also confirms the filter scope is titles only, not body text — a meaningful clarification for an agent choosing a query 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?

States a specific verb and resource ("List the travel insurance guides published on checko.co.il") and even names the returned fields. It doesn't explicitly distinguish itself from the siblings get_guide and get_faq, though the plural 'list' vs. singular 'get' makes the split inferable.

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 word "optionally" implies the search term is a filter rather than a requirement, which is useful, but there is no explicit statement of when to call this versus get_guide for a single guide or get_faq. Usage is implied, not spelled out.

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