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

Annotations already cover the safety profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false), so the bar is lower. The description still adds material behavior: an archived record is reopened and marked submitted (a non-obvious side effect on prior state) and the exact permission/plan requirements. It stops short of saying what happens when the record is already submitted or whether the receipt is validated.

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: what is recorded, the proof variants, then the archived-record side effect and prerequisites. Nothing is redundant and the core action is 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?

For a three-parameter nested mutation with no output schema, the description covers the action, both payload variants, the reopen-and-mark side effect, and auth/plan prerequisites. Remaining gaps are edge-case behavior (already-submitted records, error modes) rather than anything that would block a correct call.

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 largely does: it explains that submittedAt accompanies the record and that proof is a discriminated shape where receipt_page carries url and receiptText while manual takes an optional note. It does not mention that note/receiptText are length-capped or that 'kind' is the required discriminator, but the semantic mapping of the nested object is covered.

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 names a specific verb ('Records the application as submitted') and resource, and enumerates the two proof shapes (receipt_page vs manual). It is clear this stores submission evidence rather than performing the submission itself, though it never names the sibling it differs from (getfund_submit_application, getfund_approve_submission).

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 the precondition 'Needs applications:write and the Autopilot plan' and states the archived-record case, which is real usage context. However, there is no explicit statement of when to call this instead of getfund_submit_application or getfund_approve_submission, so the agent must infer routing from the names alone.

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