Fast GST Refund

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely new behavioral context: data-anonymization requirements (send row numbers only, keep names/GSTINs/certificate numbers local) and batch size limits. That is real value beyond the structured fields.

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 tight sentences with no filler; the enumeration of checks leads, followed by input constraints and then limits. Efficient and front-loaded, though the limits sentence partially duplicates the schema's maxItems constraints.

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?

An output schema exists, so return values need not be described. The description supplies the checks performed, the input privacy contract, and the size ceilings for a purely computational validator, which is close to complete; only the meaning of the allocation row-linkage is left to inference.

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%, so the description must carry parameter meaning, and it partially does: it specifies that rows are anonymous row numbers and amounts are integer INR paise, which resolves the unit ambiguity that the schema's bare 'amountPaise' naming leaves. It does not, however, explain the invoiceRow/receiptRow linkage semantics of the allocations array, leaving the most complex parameter under-documented.

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 (Check) and enumerates the exact validations performed: arithmetic, duplicate allocations, missing row references, overallocated receipts, invoice balances. This is far more informative than the title alone and is trivially distinguishable from the doc-reading siblings. It stops short of 5 only because it doesn't phrase the resource in a single crisp noun phrase.

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 enumerated checks imply the situation in which the tool applies (validating a reconciliation batch), and the privacy instruction is actionable usage guidance. However, there is no explicit when-to-use vs. when-not framing and no named alternative among the siblings.

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, destructiveHint=false and a closed world, so the safety profile is fully covered structurally. The description adds only that the result is 'documented checks and correction steps', which is useful output framing but no deeper behavioral context (no rate limits, prerequisites, or failure modes).

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 tool's action before the valid-value lists, with no filler. The two issue lists are dense but each value is required to constrain the enum, so the length is justified.

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?

An output schema exists, so return values need no explanation, and the input mapping is covered. What is missing for a support-desk lookup tool is guidance on when this applies versus the sibling check tools and any prerequisite context about the uploaded document.

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%, so the description must carry the parameter burden. It does meaningful work by mapping which issue values belong to which document (e.g. receipt_allocation/corrected_retry are Statement 3, duplicate_document/gstr2b_mismatch are Annexure B) - a cross-parameter relationship the enum lists alone do not convey. It still does not explain what each issue means.

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 states a clear verb+resource (get documented checks and correction steps) and scopes it to Statement 3 / Annexure B upload errors, with the valid issue categories spelled out. It does not differentiate itself from siblings like check_receipt_allocation, which overlaps with the 'receipt_allocation' issue keyword, but the core purpose is unambiguous.

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?

There is no explicit when-to-use guidance and no mention of alternatives such as check_receipt_allocation or the refund-guide tools. The issue enumeration implies the valid inputs but gives no condition for choosing this tool over its siblings.

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, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds only a list of return categories (records, checks, next steps, guides), which is thin given the output schema already exists; no auth, rate-limit, or scoping context is provided.

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 compact sentence with no filler. It is efficient, though the action verb is buried behind the 'choose the parameters' framing rather than front-loaded.

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?

An output schema exists so return values need not be explained. However, with 0% schema description coverage and no sibling differentiation, the description leaves key gaps about enum semantics and tool selection that a complete definition would close.

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%, so the description carries the full burden for the two enum parameters. It names them generically as 'stage' and 'preparation topic' but never explains what values like 'statement3', 'annexureb', 'notice', or 'filed' mean or how they combine, leaving the enum meaning to inference.

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 states a specific verb and resource: retrieve records, checks, next steps and guides for a service-export refund checklist. It conveys the domain well, though it does not explicitly distinguish itself from read_refund_guide or search_refund_guides.

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 only implied – the description tells the agent to 'choose the stage and topic' but gives no when-to-use guidance or comparison against sibling tools like read_refund_guide or search_refund_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 cover the safety profile (readOnly, idempotent, non-destructive, not open-world), so the bar is lower. The description adds genuinely new context: the guide is 'public' and returns Markdown with source links and a recorded source-check date, which tells the agent what to expect from the payload.

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 tight sentences, front-loaded with the action and resource, followed by the return shape. No filler or redundancy whatsoever.

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 an output schema and full safety annotations, the essentials (purpose, input source, return nature) are present. Only minor gaps remain, such as failure behavior for an unknown slug, which is outside what the structured fields state.

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%, so the description must carry the parameter semantics. It usefully explains where the slug originates (search_refund_guides), but says nothing about its expected format, even though the schema enforces a lowercase-hyphen pattern and 100-char limit. Partial compensation only.

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 ('Retrieve a public guide') and names the sibling that supplies the slug, so an agent can tell it apart from search_refund_guides. Differentiation from get_refund_checklist is only implicit via the word 'guide', keeping it short of a perfect 5.

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 'using a slug from search_refund_guides' establishes a clear precondition and workflow (search first, then read), which is exactly the guidance an agent needs. There are no explicit exclusions or when-not-to-use statements, so it falls just short of 5.

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 closed-world scope, so the safety profile is covered. The description adds a real compliance constraint (no PII in queries), which is useful, but says nothing about matching behavior, ranking, or result scope beyond that.

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 the action and followed by the input constraint. No wasted text, though 'public' is left slightly ambiguous.

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?

An output schema exists, so return values need no explanation, and the privacy constraint is present. However, with zero schema description coverage the agent still lacks any guidance on the limit parameter or what kind of keyword matching to expect.

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 0%, so the description must compensate. It partially does for 'query' ('by preparation topic', general keywords), but gives no syntax hint and entirely omits 'limit' (default 5, max 10), leaving half the parameters unexplained.

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 ('Find public guidance') scoped by 'preparation topic', which is enough to separate it from read_refund_guide and get_refund_checklist, which are retrieval/checklist tools rather than search. It does not explicitly name those siblings as alternatives, so it stops short of a 5.

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 gives an input constraint ('general keywords only, without taxpayer identifiers') but no when-to-use vs when-not-to-use framing and never mentions read_refund_guide or get_refund_checklist as the natural follow-ups. Usage is only implied.

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