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

Annotations already declare this a safe, idempotent, catalog-bound read, so the bar is lower. The description still adds real value beyond them: it enumerates what is returned (stable URL, brand name, img tag, brand page), discloses the not-found path with fallback_url serving a favicon or name tile, and warns that recolour variants only exist for SVG — a constraint an agent would otherwise hit at runtime.

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?

Everything is front-loaded: purpose, return payload, then the two parameter glosses, then the failure branch. It is a single dense semicolon-joined block rather than clean sentences, which slightly hurts scanability, but no clause is filler.

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 three-parameter lookup with a full output schema and complete annotation coverage, the description covers input acceptability, enum intent, return contents, and the miss case. The only omission is sibling routing guidance, which is a usage concern rather than a completeness gap in the tool's own contract.

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%, so baseline is 3, but the description adds meaning the schema does not: 'base (original colours)' glosses the enum value, 'dark (for dark backgrounds)' explains when that variant is appropriate, and the SVG-only restriction on recolour variants is spelled out rather than left implicit. It does not repeat the schema's 512 px detail for png, which is fine.

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 opens with a specific verb and resource: 'Look up the logo of a company by its domain', plus a concrete example (stripe.com). It implicitly separates itself from get_favicon via the fallback mention, but never names either sibling, so an agent must infer that search_logos exists for domain discovery.

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?

Usage context is implied rather than stated: the domain example and the 'if the brand is not in the catalog' branch tell the agent what inputs are acceptable and what happens on a miss. There is no explicit guidance on when to prefer get_favicon or search_logos, which is the main routing decision an agent faces with these siblings.

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