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

Annotations declare destructiveHint=true and idempotentHint=true, and the description goes well beyond that: it discloses full-list replacement (a stage left out is removed), a guardrail (a stage holding an open deal is not removed), and a validation rule (a new open stage is refused without meaning). This is exactly the destructive-behavior context an agent needs before overwriting a pipeline.

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?

Every sentence carries operational meaning and the destructive reconciliation rule is front-loaded. The prose is occasionally hard to parse ('a stage kept keeps its own when meaning is left out'), which costs some readability, but there is no 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 destructive, no-output-schema mutation with low schema coverage, the description is thorough about replacement semantics, removal guardrails, and the meaning requirement. It does not cover auth/permission needs or the fate of deals attached to removed stages, but for a 4-parameter tool it is substantially 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 description coverage is only 25%, so the description must carry the load, and it largely does: it explains id presence/absence (keep vs add vs remove), the meaning requirement per kind, and what is_default and name represent. It adds substantial meaning beyond the schema, though name gets no semantic treatment and the per-kind meaning rule is phrased densely.

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 names a specific verb+resource ('Save a pipeline') and immediately defines the operation's scope: name, default flag, and the entire ordered stage list with keep/add/remove reconciliation. An agent can tell this is a full-replacement save of an existing pipeline (pipeline_id is required), but it never explicitly contrasts itself with siblings like create_a_pipeline or delete_a_pipeline, so brother differentiation is left to inference.

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 implied through the reconciliation rules (include id to keep, omit to add, leave out to delete) rather than stated as when-to-use guidance. There is no explicit statement of when to prefer this over create_a_pipeline or list_stages, though the required pipeline_id and detailed stage semantics do imply update semantics.

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