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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the bar is lower. The description still adds real value beyond them: it discloses the miss case ('found is false') and the size-snapping behavior of the returned PNG, both of which the agent needs to interpret results.

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?

Three short sentences, front-loaded with the identity of the tool, then the return shape, then the failure case. No padding or redundant framing.

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?

This is a low-complexity read tool with an output schema that already documents the return payload, so the description need not explain it. The only meaningful omission is sibling differentiation from get_logo/search_logos, which leaves the agent to guess between them.

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 both parameters are already documented, including the 128/256/512/1024 snapping and the accepted URL or www. prefix. The description restates the snapping behavior rather than adding new meaning, so the baseline of 3 applies.

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: 'Get the favicon (square icon) of a company by domain', with a parenthetical disambiguating what a favicon is. It does not, however, differentiate itself from the sibling get_logo, which an agent would reasonably think is the same thing.

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 is only implied by the noun 'favicon'; there is no explicit statement of when to pick this over get_logo or search_logos. The only conditional guidance is a behavioral one (brand absent from catalog), not a tool-selection one.

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