create_opportunity

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

Annotations only carry readOnlyHint=false and destructiveHint=false, so the description carries the transparency burden and does substantial work: it discloses that tenant automation rules can mutate owner/team post-create, that pipeline is inferred rather than set directly, and notes wire-verified behaviors. No contradiction with annotations — 'create' aligns with readOnlyHint=false and non-destructive intent. Strong behavioral disclosure well beyond the minimal 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 three-sentence description is efficient and front-loaded: purpose first, then core constraints (partyId/milestoneId, value/currency coupling), then discovery and alternative tool routing. No wasted sentences at the top level; the verbosity lives in the schema's per-parameter descriptions, which is appropriate placement.

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 13-parameter tool with nested objects and no output schema, the description covers the essentials (party linkage, stage pinning, value rules, discovery path, multi-party handling) but has two gaps: the 'requires partyId and milestoneId' claim conflicts with the schema's required:[name], which could mislead an agent about mandatory inputs, and there is no statement about what the call returns on success. These prevent full callability confidence for a tool of this complexity.

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 69%, placing the baseline at 3. The description adds value on partyId and milestoneId (pinning stage, pipeline inference) but partially repeats the schema's own rich descriptions (currency-required-when-amount, list_pipelines discovery). A notable discrepancy: the description asserts 'Requires partyId and milestoneId' while the schema marks only name as required — a factual mismatch that weakens the otherwise helpful parameter guidance.

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 (Create), resource (opportunity), and linkage scope (linked to a party), clearly distinguishing it from siblings like update_opportunity, delete_opportunity, and batch_update_opportunity. The description goes further by naming the two key inputs (partyId, milestoneId) and explaining the milestone→pipeline inference, so an agent knows exactly what this creation tool is for.

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?

Provides concrete guidance: discover milestone ids via list_pipelines + list_milestones first, and use add_additional_party for multi-party deals — explicitly routing to a sibling. It also notes the chained batch_update_opportunity workaround for milestone automation side-effects. It doesn't enumerate when to favor update_opportunity or batch_update_opportunity for modifications, but the creation-vs-alternative guidance is present and actionable.

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