Send email

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

Annotations already declare readOnlyHint=false and openWorldHint=true, so the write-and-external-effect profile is covered structurally. The description adds genuinely new behavior: a ps_test_ key accepts and reports the email without delivering it, which an agent could not learn from the annotations. It omits any mention of rate limits or what happens on partial failure, keeping it below 5.

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 short sentences, each carrying distinct information: the action, the content-mode rule, and the test-key behavior. The most decision-relevant content (what it does) is front-loaded with zero 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 12-parameter, no-output-schema mutation tool, the description covers the core invocation shape but omits two things an agent needs: what the call returns (presumably an email id, since get_email and cancel_email are siblings) and how scheduling interacts with idempotency_key. Adequate to call correctly in the common case, incomplete for scheduling or retry workflows.

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 a middling 58%, and the description compensates by explaining the conditional relationship between subject, html/text, template_id, and variables — the single most important semantic an agent needs to build a valid call, and one the flat schema cannot express. It says nothing about cc/bcc/reply_to or scheduled_at, leaving roughly half the surface to 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?

States a specific verb and resource ("Send one email through Postilon"), and the word "one" implicitly separates it from the sibling send_batch. It does not explicitly name send_batch or explain how this differs from scheduling via scheduled_at, so sibling differentiation is present but implicit rather than stated.

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?

The description gives the two mutually exclusive content modes ("subject with html and/or text, or a template_id with variables") and notes the ps_test_ key path, which is real usage context. However it never states when to reach for this tool over send_batch, nor any prerequisites such as verified sender domains or rate limits, so the agent must infer routing.

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