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

Annotations already declare readOnlyHint/idempotent/non-destructive, so the safety profile is covered. The description adds genuinely new behavior: this read never grants access, never creates a collection, and selection is automatic only with exactly one writable target. That is meaningful context beyond the annotations without contradicting them.

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?

Five short sentences, front-loaded with the verb and resource, and every sentence carries a distinct constraint (scope, authorization, auto-selection, read-only nature, separation from ingestion). No filler, though the closing sentence is somewhat tangential to the call itself.

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 no output schema, the description must convey what comes back, and it does signal a list of writable collections plus the single-collection auto-selection rule. For a one-parameter read tool with full annotation coverage this is close to complete, though it does not describe the shape of each collection entry.

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?

Single projectId parameter with 100% schema description coverage, including pattern, length bounds and a note that it is a project/mapping ID rather than a local path. The schema does the heavy lifting and the description adds nothing further, so the baseline 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?

States a specific verb and resource with scope: 'List the existing business-library collections this dossier can write to.' This distinguishes it from generic library tools, though it never names a sibling tool (e.g. dossier_library_access, library) to sharpen the boundary, keeping it short of a 5.

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?

Gives real usage conditions: select a collection authorized by the responsible person, and auto-selection happens only when exactly one is writable. It also excludes adjacent concerns ('Ingestion is separate from reading, analysis and approval'), but names no alternative tool to redirect to, so it falls shy of explicit when/when-not routing.

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