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

No annotations are supplied, so the description carries the full burden, and it does substantial work: the 409 refusal condition on delete, the requirement of at least one open/won/lost stage with won and lost after all open stages, default-stage seeding on create, and the Professional-plan gating that makes writes 403 while reads stay open. It does not describe list pagination or result ordering, which are the remaining behavioral gaps for a no-annotation tool.

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?

Front-loaded with the domain definition before any action list, then a scannable per-action bullet block, then two short 'note' paragraphs for constraints and plan gating. Every sentence carries information an agent needs; nothing is padding, despite the length the six-action surface requires.

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?

With 14 parameters, nested objects, no annotations and no output schema, the definition still covers the high-risk behaviors an agent needs: destructive-delete precondition, plan-gating failure mode, and stage-ordering validity. It also summarizes what 'summary' returns (per-stage counts, open amounts, 30-day won/lost totals), compensating for the absent output schema. The list/get return shape and pagination behavior remain unspecified.

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 of 3 applies: enum values, the 24-hex pipelineId pattern, stage constraints and the currency null-clears-to-account-default rule are all already documented in the schema. The description reinforces the ordering rule for the stages array and the 'fed by one device' meaning of the device filter, but adds little that is not already in the structured field 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?

The description states a specific verb+resource ('sales pipeline management') and defines the domain concept ('a pipeline is a sales board: an ordered list of stages that deals move through'). It also implicitly separates itself from the sibling manage_whatsapp_deals: this tool manages the board, not the deals. The six enumerated actions remove any ambiguity about the scope of 'manage'.

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?

Each of the six actions is given a one-line explanation of what it does and, importantly, when it fails ('delete: refused with 409 while it still holds open deals'). The subscription note tells the agent when writes will 403 vs when reads still work, which is actionable usage guidance. It stops short of explicitly pointing at a sibling for per-deal work, which keeps it from a 5.

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