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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, so the safety profile is established. The description adds a useful nuance that 'declared file versions remain distinct from backend-authoritative versions,' informing the agent that data may not reflect backend truth. This is valuable context, though it does not explain further implications or edge cases.

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 compact at two sentences and front-loads the main purpose. The second sentence adds an important nuance without excessive length. However, the phrase 'exact requirement quotes versus interpretations' is somewhat awkward and could be clearer, preventing a top score.

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 one-parameter, read-only tool, the description names the major data categories returned. However, with no output schema and no return-format explanation, the agent may not fully understand what 'adaptive response sections' contain or how to interpret the declared-versus-backend distinction. It is adequate but leaves meaningful gaps.

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% and the projectId parameter has a detailed description ('returned by list or create dossier, never a local path'). The tool description adds no parameter-specific meaning, so the baseline of 3 applies.

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 uses the verb 'Read' with a specific resource type ('dossier references') and enumerates concrete contents: source inventory, frozen citation locators, requirement quotes versus interpretations, and adaptive response sections. It is not a tautology and is distinguishable from siblings by its focus on references, though it does not explicitly differentiate itself from other read_dossier_* tools.

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?

No guidance is provided about when to use this tool versus alternatives such as read_requirement_coverage, read_document_coverage, or read_document_plan. The description only implies a read operation but gives no context, prerequisites, or exclusions, leaving the agent to infer selection among many similarly named read tools.

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