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

With no annotations, the description carries the transparency burden and largely meets it: it discloses that prepare returns the offer and offerHash, that submit sends a signed Accept and 'activates the session', and that auth is a signed GET vs signed POST depending on mode. It does not detail failure behavior or what the submit response contains, but the main side effects and sequencing are clear.

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 dense and front-loads the tool's role before explaining the two modes. The final verify_agent sentence is useful guidance rather than fluff, though the long mid-sentence parenthetical makes it slightly harder to scan.

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 complex 6-parameter tool with nested objects, no output schema, and no annotations, the description covers the essential decision sequence: inspect with prepare, sign the correct object, submit with a signed POST, and optionally verify the counterparty first. It could be more explicit about the inviteId source and submit response, but an agent has enough to proceed correctly.

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 only 50%, but the description adds real meaning beyond the schema: it explains mode=prepare vs mode=submit, when token is required for open invites, how auth differs between modes, and that offerHash should be signed. Some parameters like inviteId are still only inferred from the tool name, but the core execution flow is clarified.

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 opens by naming the resource ('accept an invite') and explicitly positions it as 'the other half of start_session/invite_counterparty', differentiating it from sibling tools. It distinguishes direct vs open invites and names the two modes, so an agent knows exactly what this tool does.

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 clear context: use prepare to inspect the offer/hash before building the Accept, then submit to activate the session. It also recommends verify_agent as a pre-acceptance validation step with the initiator's agentId, though it does not explicitly state when to avoid this tool in favor of sibling tools.

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