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

Annotations already declare readOnlyHint=false, idempotentHint=false, destructiveHint=false, and openWorldHint=true. The description adds valuable behavioral context: the send goes through the provider for real, test sends don't count toward monthly quota but a daily allowance applies, and they never appear in feeds. It also discloses the return shape ({ sendId }). This goes beyond the annotations without contradicting them.

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 compact and front-loaded: the core action and endpoint appear in the first sentence, followed by the most important caveat (real send, use controlled recipient), then quota/feed behavior, then return value. Every sentence earns its place; no filler or repetition of schema details.

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 tool with no output schema, the description covers the return value ({ sendId }), the real-world side effect, quota implications, feed visibility, and recipient guidance. The schema covers parameter shapes thoroughly. The only minor gap is that it doesn't explicitly state what happens on failure, but the schema's 400 note and the reference to get_send_status provide enough context. Overall, an agent has everything needed to invoke 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 the baseline is 3. The description adds meaningful context beyond the schema: it explains that params drive section blocks, that missing required params are rejected with a 400 naming them, and it details the recipient shape per channel type (including that Ray keeps no device registry and webhooks use {}). This is genuinely helpful semantic enrichment.

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 states a specific verb ('Send a real test'), a specific resource ('a template's PUBLISHED version'), and the exact endpoint (POST /templates/{id}/test-send). It clearly distinguishes this from send_notification and other template tools by emphasizing it tests the published version to one recipient. The write scope is also disclosed.

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 explicitly says when to use this tool: to send a real test of a template's published version to one recipient. It warns to use a recipient the user controls, and notes the daily allowance vs monthly quota distinction. It also references get_send_status for follow-up, and the schema notes channelConfigId must match the template's channelKind, which guides correct selection.

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