BeYadCha Israeli medical rights

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

Annotations already cover the safety profile (readOnly, non-destructive, idempotent, closed-world), so the description's added value is elsewhere: it commits to using only ranges and categories and never names, ID numbers, or medical records, and it promises a list of missing answers. The 'indicative only' caveat correctly frames the output as non-binding, which annotations cannot express.

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?

Four sentences, front-loaded with the core promise, then privacy, then the missing-input behavior, then the disclaimer. No filler sentences, though the route enumeration in sentence one partly duplicates the rightType enum in the schema.

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 35-parameter, route-conditional tool with no output schema, the description leaves the conditional structure implicit: it never says that only the fields for the chosen route matter, relying on per-parameter schema notes to convey that. It does cover the return-side essentials (missing answers surfaced, results indicative) adequately.

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 per-field descriptions and enum labels, so the schema carries parameter meaning; the description adds nothing field-level beyond naming the four routes. Its useful contribution is the behavioral note that missing required answers are echoed back rather than failing, which shapes how the agent collects input.

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 ('Rough, anonymous estimate of Israeli benefits') and enumerates the four routes it covers, so the agent knows exactly what is produced and at what fidelity. It does not name or distinguish itself from the siblings get_rights_guide and search_rights_knowledge, leaving the agent to infer the split between estimating numbers versus retrieving guidance.

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?

Usage is implied rather than stated: 'rough', 'anonymous', 'indicative only' signal this is a first-pass estimator, not an authoritative determination. There is no explicit when-to-use/when-not or any mention of the alternative sibling tools, and the one-route-per-call constraint is stated but not contrasted with any other path.

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 cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description nonetheless adds the genuinely non-obvious behavior that long guides return an overview plus section list first and require a second call with "section", which prevents an agent from assuming a single call yields full content. It doesn't cover what happens for an unknown id, but the core read semantics are well disclosed.

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, front-loaded with the verb and resource, then the paging behavior, then what the content contains. Every sentence carries distinct 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 two-parameter read tool with no output schema, the description fully covers what is returned (overview plus section list, then section content) and what each guide holds (eligibility, amounts with dates, claim process, forms, official sources). Nothing needed to call it correctly is missing.

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 examples for both parameters, so the baseline is 3. The description goes beyond that by explaining the two-step semantics of "section" — the first call returns a section list, and "section" is used on a subsequent call — which is a usage pattern the schema does not convey. It also clarifies id provenance, adding real meaning beyond the field descriptions.

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?

"Read one Hebrew rights guide by id" names a specific verb and resource, and the id-provenance clause distinguishes it from search_rights_knowledge without opening either schema. An agent can immediately tell this is the retrieval step that follows a search.

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 states where ids come from (search_rights_knowledge results, or a guide referenced inside another guide) and describes the follow-up call needed to drill into a section, which implies the search-then-read workflow. It stops short of an explicit "use search_rights_knowledge instead when you don't have an id" exclusion, but the routing is clear enough to act on.

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 the safety profile needs no restatement. The description adds real value beyond that: it discloses the shape of the result (best matching guides plus their ids) and a behavioral quirk of the search engine (Hebrew queries perform better), which is not visible in any structured field.

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, front-loaded with the verb and corpus, no filler. The long parenthetical topic list consumes most of the length but earns its place by defining the retrieval scope for an open-domain query. Slight density cost, no waste.

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 two-parameter search tool with no output schema, the description covers the corpus, the input language strategy, and the rough return shape (matching guides with ids). The one meaningful omission is not connecting those ids to get_rights_guide, which is exactly the handoff an agent needs after a search.

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 both parameters are already documented in-schema, including a Hebrew example query and the limit default/maximum. The description's only additional signal is the general Hebrew-query preference, which the schema's "preferably Hebrew" already conveys. Baseline 3 applies since the 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?

Names a specific verb and resource ("Search a Hebrew knowledge base") and scopes the corpus precisely with an enumerated list of domains (National Insurance, medical committees, tax exemption, work injury, conditions, forms). An agent can tell this is a topical search tool rather than a fetch-by-id tool. It stops short of naming the sibling get_rights_guide as the follow-up step, so sibling differentiation is only implied by "with their ids".

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?

"Query in Hebrew works best" is a useful operative hint, and "Returns the best matching guides with their ids" implies a search-then-fetch flow. But there is no explicit statement of when to choose this over estimate_benefits, and no statement that the returned ids should be passed to get_rights_guide. Usage is inferable rather than stated.

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