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

Goes well beyond the annotations by explaining that the capability is short-lived and time-bound, that each call mints a new one, and that retries will not return the same token. It also names the returned fields (access_capability and expiry) and the recipient's authentication requirement — behavior an agent cannot infer from readOnlyHint/idempotentHint/openWorldHint alone.

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 front-loaded sentences, each carrying distinct information: what is created, what it is not, and the operational caveats. No filler or restatement of the tool name.

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?

Although there is no output schema, the description names the return values, the recipient-side follow-up tool, the authentication prerequisite, and the non-idempotency caveat. Nothing material is missing for an agent to call this 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 description coverage is 100%, so note_id, recipient_agent_id, and ttl_seconds are already fully documented. The description reinforces the short-lived/expiry concept but adds no syntax, bounds, or format detail beyond the schema — the baseline 3 for schema-documented parameters.

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 precise verb+resource+scope: 'Create a short-lived read capability for one note authored by the current authenticated agent and one recipient.' It also bounds what it is not ('does not publish the note or grant access to other notes'), which separates it from publish-style siblings and from the recipient-side tool it names.

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?

Gives clear operational context: the recipient must authenticate and then call get_shared_cassie_note, and the note is not published. Exclusions are present ('does not publish... or grant access to other notes'), but there is no explicit statement of when this tool should be preferred over siblings like submit_cassie_note or exchange_cassie_culture_seed.

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