Checko — travel insurance comparison

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, and the closing 'Read-only' merely restates them. The one piece of added context is domain knowledge that medical extensions are excluded from this catalog, which is genuinely useful but thin for a catalog-listing tool.

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, front-loaded with what is listed and followed by the one exclusion that matters. The trailing 'Read-only' is redundant with annotations and does not earn 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?

No output schema exists, but the description indicates the result contains option names as used on Checko, which is enough to plan a follow-up comparison call. It could say more about what each entry contains, but nothing blocking is missing for a parameterless catalog read.

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 there is nothing for the description to disambiguate; baseline 4 applies. It correctly implies the call is unfiltered and returns the full option set.

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: lists the optional activities and extras available in Checko's travel insurance comparison. The resource is clearly distinct from siblings such as list_destinations and list_insurers, so the agent can pick correctly without opening a 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 exclusion 'Medical extensions are not offered here' tells the agent what this tool won't return, but gives no alternative for medical extensions and no explicit when-to-use framing relative to start_travel_insurance_comparison. Usage is only implied by context.

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, destructiveHint=false, and openWorldHint=false, so 'Read-only' in the description merely restates structured data. The genuinely additive detail is that search terms may be Hebrew or English; it says nothing about result size, ordering, or pagination, which is acceptable given the annotation coverage.

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 resource and scope, followed by the optional filter and safety hint. No filler or redundancy.

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 one-optional-parameter lookup with full annotation coverage and no output schema, the description covers purpose, filtering, and language support adequately. The only minor gap is that it does not characterize what a returned 'destination' entry contains, which matters slightly given there is no 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 optional parameter is already documented with examples. The description adds value beyond the schema by stating that matching works in both Hebrew and English, which the schema only hints at via a single Hebrew example.

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 ('Lists the destination regions and countries') plus the domain constraint ('that Checko's travel insurance comparison accepts'). The entity is clearly distinct from the sibling tools list_insurers, list_coverage_options, and start_travel_insurance_comparison without needing to name 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?

The word 'optionally' makes clear the query filter is not required, and '(Hebrew or English)' hints at accepted input. But there is no explicit when-to-use guidance, no mention of prerequisites, and no named alternative for the adjacent lookup tools.

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, openWorldHint=false and destructiveHint=false, so safety is covered. The description adds a genuinely useful behavioral fact beyond the annotations: the output contains no prices, so an agent knows to go to the comparison tool for cost. It does not mention result size or ordering, a minor omission.

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 the scope front-loaded and the "no prices" caveat second. Every clause carries information 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 zero-parameter, non-destructive enumeration with no output schema, the description covers what is returned (a list of insurer names) and what it is scoped to (travel offers Checko compares). It stops short of describing result shape or how the insurers relate to the coverage options returned by siblings, which leaves a small gap for an agent planning a multi-call workflow.

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 there is nothing for the description to explain; baseline 4 applies. Nothing in the description contradicts or muddies the empty 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?

States a specific verb ("Lists") and resource ("Israeli insurers whose travel insurance offers Checko compares"), which an agent can distinguish from list_coverage_options and list_destinations by resource alone. No sibling is named explicitly, so differentiation is implicit rather than spelled out.

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-only; no prices" implicitly signals this is for discovering which insurers exist, and that pricing must come from start_travel_insurance_comparison, but the description never says when to call this versus list_coverage_options or list_destinations. Usage has to be inferred from the resource name.

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 say non-destructive and non-idempotent; the description adds real value beyond them by disclosing that no prices are returned, that no PII (names, contacts, birth dates, medical) is accepted, and that the flow continues off-site. What it does not cover is repeat-call behavior (a new card each time?) or whether the returned link expires, which matters given idempotentHint=false.

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?

Three sentences, no filler: capability and output first, then the input contract, then the explicit limitation that no prices come back. Each sentence carries information an agent needs before calling.

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 describes the return shape (trip card plus link, no prices) and the privacy boundary, which is enough to call it correctly. Minor gaps remain around link lifetime and what the card contains besides the URL.

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 per-field meaning and formats are already documented; the description adds the useful constraint that only trip details are accepted and that identity/medical fields are deliberately absent, which stops an agent from trying to inject them. It gives no guidance on destination granularity versus the list_destinations sibling, so it stays modest rather than additive on parameter 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?

States a specific verb and resource (prepares a travel insurance comparison on Checko) plus the scope (trip abroad from Israel) and the concrete output (a trip card with a link to checko.co.il). This is clearly distinguishable from the list_* siblings, which only enumerate options rather than starting a comparison.

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 clear when this applies - an Israel-origin trip abroad - and explains the hand-off: the user finishes traveller details and consent on Checko. It does not explicitly route the agent away from list_destinations/list_insurers or say whether those should be called first, so the variant selection is only implied.

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