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

Annotations already declare destructiveHint=true, idempotentHint=true, and readOnlyHint=false, but the description adds real value beyond them: a sent config fully replaces the stored one, and blank secret keys preserve the stored secret. That replacement/secret-retention rule is exactly the kind of behavior an agent cannot infer from the structured fields.

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, front-loaded sentences with no filler; the partial-update mode and the config replacement caveat are stated in the order an agent needs them. Slightly terse for a 10-parameter destructive mutation, but nothing is wasted.

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?

For a destructive, idempotent mutation with a nested object and no output schema, the description covers the riskiest aspect (config replacement and secret retention) but omits what happens to fields not supplied, whether other field updates are reversible, and any permission requirements. Adequate but with clear gaps.

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?

With 10 parameters, 50% schema coverage, and a nested config object, the description explains only the config parameter's merge semantics. The other nine parameters (name, tags, status, currency, group_id, platform, send_value, payout_percent) get no added meaning beyond the schema, though the config explanation is genuinely valuable and compensates in part.

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 ("Edit a pixel") and clarifies the update mode with "(partial)". It does not explicitly differentiate from siblings like create_pixel, get_pixel, or update_offer, but the purpose is unambiguous on its own.

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?

"(partial)" implies this operates on an existing pixel and only touches supplied fields, which is useful implied guidance. However, there is no explicit when-to-use/when-not guidance, no mention of required prerequisites (pixel must exist, permissions), and no pointer to create_pixel for new pixels.

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