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

The description provides extensive behavioral rules beyond the annotations: preserve original files, reference source IDs, distinguish document kind from role, scope supersession to clauses/lots, keep company knowledge internal, model internal fields, retain stable IDs and existing contributions, never infer extraction or approval, and require review for new definitions. This fully discloses how the tool behaves, complementing the annotations (write, idempotent, destructive) without contradiction.

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 dense but appropriately structured: it opens with the main purpose and then lists behavioral imperatives in a logical order. Each clause adds distinct meaning without redundancy. For a tool with this complexity, the length is justified; it is not bloated but efficient in conveying many rules.

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?

Given the tool's complexity (6 parameters, nested objects, many fields), the description covers all critical behavioral aspects: preservation, source referencing, kind/role distinction, supersession scope, confidentiality, field modeling, ID stability, inference limitations, review requirements, and integration with submit_analysis. No output schema exists, but for a mutation tool this is acceptable. The description is comprehensive for an agent to correctly invoke it.

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 only 33%, and many nested fields lack descriptions. The description compensates by explaining the meaning of key concepts like kind vs. role, scoping supersession, internal fields, and binding buyer text fields to responseOutline. It clarifies how to structure the definition and the roles of revision parameters (analysisRevision, contextRevision) implicitly. While not every parameter is detailed, the description adds substantial semantic value.

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 clearly states the tool's purpose: 'Define this specific dossier from the current analysis.' It specifies the resource (dossier workspace) and action (define) with context, and distinguishes from generic 'create' or 'contribute' tools by emphasizing it works from the current analysis. The detailed behavioral constraints further clarify its scope.

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 implies when to use it (when defining a dossier from analysis) but does not explicitly compare with sibling tools like create_dossier or contribute_dossier. It states a new definition or context requires review, which hints at conditions, but lacks clear 'use X instead' guidance. This leaves some ambiguity for an agent selecting among many related tools.

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