Reconcile Form 16 vs AIS vs 26AS

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered; the description adds real value beyond that by disclosing that missing inputs yield skipped checks rather than errors, and that output includes per-income-head grouping of 26AS TDS. It stops short of describing the result shape or how mismatches are counted/severity-ranked.

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 purpose and the regulatory rationale (143(1)(a)/139(9)), then a compact enumeration of checks. It is dense and long-ish but nearly every clause names a distinct check or behavior, with little 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 read-only, no-output-schema, all-optional-params tool, the description covers purpose, all checks, and degenerate-input behavior. The main gap is that the return value's structure (fields of the mismatch report) is only implied by naming, not stated.

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 schema already documents all five parameters including the nested AIS/Form 16/26AS/return shapes. The description adds only the semantic framing of 26AS as "the ledger of record" and notes which document each check consumes; the fy parameter and the specific field mappings are left entirely to the schema. 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?

States a specific verb-like operation (cross-document mismatch report) and enumerates the exact checks performed: TDS claimed vs 26AS deposited, missing-employer detection, AIS vs declared, Form 16 vs 26AS per-TAN, and 26AS rows missing gross. This is clearly distinguishable from siblings like parse_form26as or parse_ais, which produce inputs rather than reconcile 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?

"Pass whichever documents you have; checks needing missing inputs are reported as skipped" gives clear operating context and explains partial-input behavior. It does not explicitly name the sibling parse tools as the source of the inputs or state when not to use it, so it stops short of a 5.

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