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

With no annotations, the description carries the full behavioral burden, and it does disclose the most consequential trait: this is a partial patch, but `steps` wholesale replaces the step list and `run_at: null` clears the value, so silent data loss is possible. It omits other traits an agent needs for a mutation with no safety hints — permission/auth requirements, whether changes are reversible, error behavior on unknown field keys, and the response shape.

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, front-loaded with the verb, then the allowed-key enumeration, then the one destructive caveat. No filler; every clause carries information an agent would otherwise have to guess.

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 zero annotations, no output schema, and a nested free-form object parameter, the description covers the field vocabulary but leaves gaps: return value, error modes, permission requirements, and per-field types. Adequate to invoke correctly in the happy path, not complete.

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 0% and `fields` is an untyped free-form object with additionalProperties: true, so the description is the only source of truth — and it enumerates all eleven accepted keys plus the two special semantics (null clears run_at, steps replaces the list). It does not give per-key types or formats (cron_expr syntax, task_variables shape, which flags are booleans) and says nothing about pipeline_id, so it is strong but not complete compensation.

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?

"Patch a pipeline" gives a specific verb (patch/partial update) and resource, and the sibling set (pipeline_create, pipeline_delete, pipeline_run) makes the CRUD role obvious from the name plus verb. It stops short of naming a sibling it might be confused with (e.g. pipeline_group_update, schedule_update) in prose, but the intent is unambiguous.

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?

Usage is only implied: "Patch" signals a partial update of an existing pipeline rather than a create/delete, and the field-level notes (run_at null clears, steps replaces the whole list) hint at how to use it correctly. There is no explicit when-to-use/when-not statement, no mention of prerequisites such as ownership or permissions, and no pointer to alternatives like pipeline_create.

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