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

Annotations are all false, so the description carries the full burden. It discloses project-scoping, the return of project identity, and the default behavior when pages are omitted. However, it does not clarify whether the operation modifies state (e.g., marking pages as delivered) or if it is idempotent, given readOnlyHint=false and idempotentHint=false. This lack of side-effect disclosure is a notable gap.

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 front-loaded with 'PROJECT-SCOPED' and is logically structured. However, it is somewhat verbose with jargon like 'persisted hierarchical visual storyboard' and 'logical turn,' which could be simplified. It's not wasteful, but not as crisp as the ideal.

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 two parameters, no output schema, and sparse annotations, the description covers purpose, usage, and parameter behavior adequately. It does not detail the exact return structure beyond mentioning project identity, but this is likely sufficient for an agent to invoke it correctly. The large sibling list is addressed by the clear usage condition.

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 50% (project_id has a description; pages does not). The description compensates by explaining that pages are integer labels, can be omitted to open all undelivered pages, and are 'transport batches.' It also reinforces project_id's role as required immutable scope. This adds meaning beyond the schema.

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: opening labeled pages from a persisted hierarchical visual storyboard. It uses a specific verb ('open'), names the resource ('pages'), and distinguishes it from siblings by noting it retrieves actual pixels for evidence IDs not in the initial orientation page. This is explicit and unambiguous.

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 provides a clear usage condition: 'use this whenever you need the actual pixels for an evidence_id not present in the initial orientation page.' It also advises to 'call repeatedly and open as many as the edit requires,' giving practical guidance. However, it does not explicitly name alternative tools or state when NOT to use it, so it's not as strong as a direct sibling comparison.

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