mailkite_update_sequence

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

Annotations only state readOnlyHint=false, which just says 'mutation'. The description goes well beyond that by disclosing version bump behavior for step changes, the fact that in-flight contacts continue on their original version, that no other edit re-pins anyone, the difference between archiving (retires everyone) and pausing (resumes later), and the API key requirement. This is exactly the behavioral context an agent needs to anticipate side effects, and it adds substantial value over the minimal annotation. No contradiction with annotations.

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 two sentences with zero fluff. The core purpose ('Edit a sequence') is front-loaded, and the subsequent sentence packs the most important behavioral consequences into a compact, scannable format. Every clause adds value – versioning, in-flight behavior, archive vs. pause distinction, and API key requirement. It is concise without being under-specified.

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 mutation tool with no output schema, this description covers the essential context: what editing does, side effects on in-flight enrollments, the distinction between pausing and archiving, and authentication requirements. It also clarifies which edits are version-bumping (steps) and which are not, which is critical for an agent to predict outcomes. Combined with the schema's parameter descriptions, nothing essential is missing for an agent to invoke the tool 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 coverage is 56% (9 parameters, some with descriptions). The description adds meaningful semantic context for the 'steps' and 'status' parameters by explaining that changing steps bumps the version and that pausing (a status value) does not re-pin contacts. It also clarifies the effect of renaming and trigger set changes, which map to 'name' and 'triggers' parameters. However, some parameters like 'from' and 'reentry' are not addressed in the description; the schema already documents those, so the description compensates reasonably for the coverage gap.

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 'Edit a sequence' – a specific verb and resource – and immediately differentiates the action from siblings by detailing what changes bump the version (steps) versus what does not (rename, pause, input signature, trigger set). This gives an agent a clear, unambiguous understanding of what the tool does and how it differs from create/delete/start/stop operations on sequences.

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 strongly implies when to use this tool (to modify a sequence) and provides crucial context about the effects of editing while sequences are in flight, such as version bumping semantics and the distinction between pausing and archiving. It does not explicitly name alternative tools or state 'use this when you need to change X', but the behavioral details effectively guide an agent's decision process, especially the note that renaming or pausing does not re-pin contacts, which is exactly the kind of nuance an agent needs.

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