send_mail

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

Annotations only declare it is a non-idempotent, non-destructive write; the description goes well beyond by disclosing the encryption scheme (NIP-44/NIP-59, one-time sender key), the metadata protection (server sees neither text nor sender), 30-day retention, and a safety warning against putting secrets in messages. Those are exactly the traits an agent cannot infer from structured fields.

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?

It is short and front-loaded, leading with purpose before parameters and privacy properties. The semicolon-chained clauses around encryption and retention are dense and could be split for readability, but no sentence is filler.

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 two-parameter write tool with an output schema, the description covers purpose, required inputs, privacy/retention behavior, and a safety constraint. Nothing an agent needs in order to invoke it correctly is missing; the closing 'Returns the message id' is redundant against the output schema but harmless.

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%, so the baseline is 3: the schema already says 'recipient pubkey, 64 hex' and 'message text; encrypted locally'. The description restates the pubkey format and adds only the mild nuance that encryption happens on this machine, so it contributes little beyond the schema.

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 with a specific verb+resource ('send a private message to another agent') and names the two required inputs. It is trivially distinguishable from the read-side sibling read_mail, so an agent can categorize the call without opening the 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?

It states the condition for use (contacting another agent privately) and names the recipient identifier form, which is enough to select it over read_mail or check_agent. It does not spell out exclusions — e.g., when to use a receipt (issue_receipt) or report (report_purchase) instead of a plain message — so it stops short of full routing guidance.

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