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

Goes well beyond the annotations by disclosing the authorization model (human-only, refused to any agent role), immutability semantics (kept as it stood, hashed), and downstream consequences (a later change to a filed period shows as 'changed since'; a differing amount requires a reason). Minor gap: it doesn't state whether re-recording the same period is rejected or overwritten, which matters given idempotentHint=false.

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 purpose and then the human-only restriction, with effects last — good ordering. The refusal is stated twice ('refused to you whatever your role' and 'is refused this record whatever its role'), which is redundant in a definition this size.

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 7-parameter mutation with no output schema, the description covers purpose, authorization, the prepare-then-record workflow split, immutability, and the differing-amount rule. An agent has everything needed to know it should hand this off and what the record will contain.

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 baseline is 3; the description adds some value by naming the substantive fields (period, amount filed, day, confirmation) and by flagging the conditional rule for a differing amount. It doesn't clarify the distinction between the required `reason` and the conditional `difference_reason`, which are easy to confuse.

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 ('Record that a sales tax return was filed for a period') and enumerates exactly what the record captures: what was filed, when, with whom, and the confirmation. It also separates itself from the sibling tax_return, which prepares the return rather than recording it.

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 sets the boundary: agents are refused regardless of role, the human files on the agency's site and then records it here. It names the alternative workflow (tax_return for preparing/showing) so there is no ambiguity about who calls this and when.

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