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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely new behavioral context beyond that: credentials are never returned (a redaction guarantee), plus the concrete shape of each row (id, name, platform). It stops short of noting pagination or result-size behavior, though the schema covers those.

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 short sentences, front-loaded with the resource and its fields. Every clause earns its place: the field list tells the agent what a row contains and the credentials clause sets a security expectation.

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?

There is no output schema, so the description's field preview and credential-redaction note usefully fill that gap for a simple, low-complexity read tool whose parameters and safety hints are fully covered by schema and annotations. Only minor items, such as whether results are paginated by default, are left to the schema.

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%, with page, search and per_page each documented including defaults and the max of 100, so the description adds nothing about parameters. Baseline 3 applies when the schema carries the full load.

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 the resource ("Pixel catalog") and previews the returned fields (id, name, platform), so an agent knows this is a read-only listing of pixels. It is clear but does not differentiate itself from siblings such as get_pixel (single pixel) or list_pixel_events (events for a pixel), which an agent must infer from the names alone.

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 when-to-use guidance, no prerequisite or exclusion statements, and no reference to alternatives like get_pixel for a single record or create_pixel for mutations. The agent must derive applicability entirely from the tool name and sibling names.

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