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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the agent knows it's safe. The description adds that it returns compact processing metadata and does not read the shared object bucket or process media, which is useful behavioral context beyond the annotations. 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?

Two sentences with no waste. The core purpose is front-loaded, followed by the explicit non-scope statement, and the cursor usage is mentioned. Every sentence adds value.

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?

The tool is a simple paginated list with a clear output schema (indicated by has output schema true). The description covers the key aspects: pagination, optional filter, scope (organization), and what it does not do. Nothing an agent needs to call it correctly is missing.

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 100% (all parameters have descriptions in the schema). The description mentions the optional project id and the cursor for pagination, but does not add new meaning beyond the schema's parameter descriptions. Baseline 3 is appropriate when the schema covers all parameters.

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 lists a bounded page of processed image batches in the signed-in organization, with optional exact project id filtering. It distinguishes from siblings by explicitly noting it does not read the shared object bucket or process media, and the sibling list (list_projects, list_templates, list_webhook_subscriptions) covers other resource types, making this specific to batches.

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 states when to use it (listing batches with optional project filter) and mentions the cursor to continue pagination. It doesn't explicitly say when not to use alternatives, but the context of siblings and the phrase 'does not read the shared object bucket or process media' implies it's a lightweight read, helping an agent decide it's not the heavy processing tool.

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