Claim Back

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and openWorldHint=false, so safety is covered. The description adds substantive domain behavior beyond that: the derivation rule (65 days = 60 from receipt + 5 presumed mailing days) and the fast-appeal cut-off (noon the day before care ends). It does not clarify what happens when both or neither date is supplied.

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?

Front-loaded with the tool's purpose, then the two input scenarios, with the precedence caveat last. Dense but every sentence carries information; the parenthetical rule explanation slightly increases cognitive load but 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?

There is no output schema, so the description correctly carries the burden of explaining results, and it does so (65 days from notice_date; noon the day before care_end_date). For a two-parameter read-only calculator this is nearly complete, with only the both-params / neither-param behavior left ambiguous.

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 params are optional, so the baseline is 3, but the description adds real meaning the schema lacks: it ties each parameter to a specific output (reconsideration deadline vs fast appeal) and identifies the source documents. The interaction rule when both are provided is still unstated.

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?

Opens with a specific verb+resource ('Calendar arithmetic for Medicare Advantage appeal deadlines'), which is unambiguous and clearly distinct from siblings claim_back_services, list_guides and read_guide. An agent can identify the tool's function from the first clause alone.

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 tells the agent exactly which input selects which scenario: notice_date for the plan reconsideration deadline, care_end_date for the fast appeal. It also states a precedence rule ('The notice's own instructions come first'). However it never names an alternative tool or states when not to use this one, so it stops short of full when/when-not 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 this a safe, read-only, idempotent operation, so the safety burden is covered. The description adds useful behavioral context beyond that: the check is free, pricing is fixed and contingent on reversal, and the tool emits an upload link rather than performing any write.

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 and both are front-loaded, with the purpose first and the usage guidance last. The parenthetical pricing clauses are dense but each carries real information; only minor tightening is possible.

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, read-only tool with no output schema, the description covers everything an agent needs: what content is returned (services, prices, upload link) and when to call it. Nothing material 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?

The schema has zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. No parameter-level detail is expected or needed here.

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 the resource (Claim Back's services and prices for a Medicare Advantage appeal) and states the concrete return artifact: the link where the user uploads their letter. It is clearly distinct from the guide- and deadline-oriented siblings, though the verb is implicit rather than a crisp action like 'retrieve' or 'get'.

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?

Explicitly states the trigger condition: 'Use it when the user wants help with an appeal or asks about Claim Back.' It gives clear context but does not exclude cases or name an alternative (e.g. appeal_deadline) for adjacent questions about deadlines or appeals.

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 is covered. The description adds value by disclosing the shape of each returned item (slug, title, one-line summary, link), which matters since there is no output schema. It does not discuss ordering or result size, so it stops short of a 5.

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 states the resource first, then the enumeration of guides, then the routing hint to read_guide. The topic list is slightly long but each item earns its place by signaling catalog coverage, so no real 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 zero-parameter catalog tool with no output schema, the description covers what is listed, the fields of each entry, and the next action. Nothing an agent needs to invoke 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?

The tool takes zero parameters, so there is nothing for the description to clarify beyond the schema; baseline for a parameterless tool 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?

States a specific verb (Lists) and resource (Claim Back's appeal guides), with scope narrowed to Medicare Advantage denials in the US. It also enumerates the guide topics covered, so an agent can distinguish this catalog tool from the sibling read_guide 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?

Explicitly gives the when: 'Use it to find the guide that answers the user's question', and names the follow-up alternative 'then read_guide'. This is a clear two-step routing instruction rather than implied usage.

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, closed-world behavior, so the safety profile is covered. The description adds what the annotations cannot: the return format (full Markdown) and that sources are embedded, which matters since there is no output schema. No rate limits or truncation behavior for very long guides are mentioned.

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, zero filler, and the output shape is front-loaded before the usage instruction. Every clause earns its place: return content, sources, usage context, and the linking directive.

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 single-parameter read tool with no output schema, the description supplies purpose, usage context, and the return format, which is enough to call it correctly. Minor gaps remain around guide length or any pagination/truncation, but nothing blocks correct invocation.

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 100% and the single slug parameter carries a description plus a closed enum of four values, so the schema does the heavy lifting. The description adds nothing about slug semantics or how to obtain it (the schema already points at list_guides). Baseline 3 applies.

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 pairs a specific verb with a specific resource: 'Returns one guide in full as Markdown, with its sources.' Singular 'one guide' implicitly separates it from list_guides, and the sources clause clarifies the payload. It never explicitly names or contrasts its siblings, so sibling differentiation is only implied.

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 gives clear context for invocation: 'Use it to answer questions about Medicare Advantage appeals accurately, and link the guide in the answer.' That is actionable guidance plus an expected follow-up action. It stops short of stating when not to use it or naming list_guides/appeal_deadline as the alternative path.

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