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

Annotations declare readOnlyHint=true, openWorldHint=false, idempotentHint=true, destructiveHint=false. The description reinforces idempotency and non-destructiveness by stating it is 'byte-identical' and 'prepare/hash/receipt only'. It adds context about the matching engine being 'deterministic' and the output being a receipt with an execution hash, which goes beyond annotations.

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?

The description is a single paragraph that front-loads the core action. It is somewhat verbose but each sentence adds value (input formats, matching algorithm, output structure). Could be slightly more concise, but it is well-structured and readable.

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?

Given the complexity of the tool (two inputs, specific matching rules, detailed output), the description covers all necessary aspects: input format constraints, matching order (EndToEndId exact then amount+date tolerance+currency), output components (matches, exceptions, receipt with digest and execution hash). Without an output schema, the description effectively explains return values, making it complete.

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 descriptions for all 4 parameters. The description adds extra context: for expectations_csv it mentions 'same strict RFC 4180 parser as the WORKBOOK-1 CSV tools', and for amount_tolerance it states 'default 0.01' (also in schema description). For statement_xml and date_tolerance_days, the description adds minimal additional value. Since schema already covers basics, the description provides modest extra semantics, warranting a 3.

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 clearly states the tool parses two inputs (camt.053 statement and CSV expectations), runs a deterministic match engine, and returns matches, exceptions, and a reconciliation receipt. It distinguishes itself from siblings like 'camt053_parse' (only parses) and 'match_confirmations' (different matching).

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 explains that this tool is for initial reconciliation (prepare/hash/receipt only) and that per-exception disposition is handled by the browser workbench. It provides context on when to use it but does not explicitly exclude alternatives or mention when not to use it.

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