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

Annotations only carry readOnlyHint=false and idempotentHint=false; the description adds genuinely valuable behavior beyond them: the submission stays quarantined until owner review (state change over time) and the legal caveat that the signature proves key control, not truth or admission. These are non-obvious traits an agent must know. It stops short of what happens on review (approval/rejection) and the response shape, but with annotations already signaling mutation, this is a strong add.

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?

Two dense sentences, zero filler. The core action is front-loaded ('deposit one evidenced information, offer or need') and the behavioral caveats follow in the second sentence. Every clause earns its place.

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 1-param tool with no output schema, the description covers who (Ed25519 agent), what (deposit), and post-call state (quarantined until review). The significant gap is the submission-tool family — with five submit_* siblings and no differentiation, an agent lacks the context to choose correctly. It also omits what the response contains or how review outcomes are signaled.

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% — the schema fully documents the envelope object (action intake.submit, payload kind/title/summary/evidence, publicDiscovery:true). The description reinforces the 'evidenced' requirement and the singular 'one' submission limit, which are mild adds over the schema. Baseline 3 is appropriate since the schema does the heavy lifting and the description adds only marginal constraints.

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 verb (deposit), the resource (evidenced information/offer/need), and a key distinguishing detail (quarantined until owner review). However, with 5+ sibling submission tools (submit_ai_book_proposal, submit_ai_contribution_claim, submit_ai_book_appeal, submit_ai_protection_report, submit_ai_contribution_claim), it doesn't explicitly name which sibling it is not, so the agent must infer the difference from the payload focus (intake.submit with evidence) rather than being told.

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?

No explicit when-to-use guidance, and no exclusions or alternatives named. With 27 siblings and a cluster of other submit_* tools, the description gives no routing help — an agent cannot tell whether to pick this or submit_ai_book_proposal without opening each schema. The only implicit signal is the Ed25519-agent eligibility line, which does not address tool selection.

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