Mark Application Submitted

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

Goes well beyond the annotations (destructiveHint=true, readOnlyHint=false, idempotentHint=false) by disclosing the terminal nature of the transition, the evidence requirement, that user_attested is the user's attestation rather than the caller's and is not server-verified, and that channel='auto' is accepted only while full automation is on. This is exactly the kind of auth/verification/mode behavior an agent needs.

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-loads the core action and terminal scope before the evidence rules, and every sentence carries information. The middle passage on user_attested is dense and slightly repetitive ('the user's attestation, not the caller's'), but not wasteful.

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 no-output-schema mutation tool, the description covers the state change, evidence/attestation requirements, verification posture, and automation-mode gating. It does not spell out what the response returns or precisely how the application link is applied, a minor gap.

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?

With 0% schema coverage the description must carry the load, and it does: it explains user_attested's meaning and substitution role, note's content ('their words' / 'naming what confirmed it'), and channel='auto' semantics. proposal_id is only implied as 'an approved proposal', leaving one small gap.

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 ('flip an approved proposal to submitted'), plus the consequential scope detail that it is terminal and links the application to applied. An agent can distinguish this state-transition from siblings like propose_application, record_decision, or resume_proposal without opening a schema.

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?

Clearly states the conditions under which the tool may be invoked: a submission_receipt must exist, or user_attested=True, or the auto channel while full automation is on. It does not name explicit alternatives (e.g., use record_decision to approve first), so it is strong context without full routing guidance.

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