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

Annotations already provide readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description reinforces 'Read-only: does not modify job state' and adds crucial details: 'The returned text field... is the source of truth — you MUST use it to count exact character positions. Character positions within each line are 0-based from the start of that line.' This exceeds annotation coverage. No 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?

Five sentences, all relevant and front-loaded. No fluff. Immediately states purpose, then read-only hint, usage order, and data semantics. Efficient and well-structured.

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?

Covers purpose, behavior, usage order, and key data semantics (0-based indexing, source of truth). Output schema exists but not shown; description mentions 'text' field. Minor lack of handling for edge cases like empty results, but overall complete for the tool's 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 description coverage is 100%, so baseline is 3. The description does not add extra semantics beyond the schema. The schema already includes guidance like 'use the latest job_id' for the job_id parameter.

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 states 'Return per-page, per-line text for identifying redaction targets.' This clearly specifies the verb (return) and resource (per-page, per-line text). It distinguishes from sibling tools like redact_by_text_range which performs actual redaction.

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?

Explicitly says 'ALWAYS call this before redact_by_text_range,' providing clear usage ordering. Also states 'Read-only: does not modify job state,' implying safe to call anytime. No explicit when-not, but the sibling tools cover different actions.

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