Update a subscription

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

Goes beyond the annotations (which only declare idempotent/non-destructive/non-readOnly) by disclosing the replace-vs-merge semantics of `headers` and `metadata` and the immutability of the flight binding — behavior an agent cannot infer from the schema or annotations. Minor gaps remain: no mention of delivery-history effects or whether a new webhookUrl is re-verified.

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 sentences, zero waste: mutable fields first, patch semantics second, the hard constraint and its workaround last. Every sentence carries information not present elsewhere.

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 6-parameter mutation tool with no output schema, the description covers what can be changed, how to send changes, and the one immutable property. It would be complete at 5 with a note on validation/re-verification of a changed webhookUrl or on whether existing deliveries are affected.

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 already 100%, so baseline is 3; the description adds real value by clarifying that `headers` and `metadata` replace the stored maps rather than merge, and by framing the operation as a partial patch so unchanged fields are left intact. That nuance is not in the schema descriptions.

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 (change) and resource (subscription) and enumerates exactly which fields are mutable (webhookUrl, events, delayThresholdMinutes, headers, metadata), which alone distinguishes it from create_subscription and get_subscription. The explicit statement that the flight is immutable further pins down the tool's scope.

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?

"Send only the fields to change" is a precise call pattern, and "create a new subscription for a different flight" names the alternative for the case this tool cannot handle. It stops short of routing the agent to pause_subscription/resume_subscription for temporary silencing, which would have earned a 5.

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