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

Annotations cover the safety profile (readOnly, idempotent, openWorld, non-destructive), and the description adds substantial behavior beyond them: the declared-vs-default source distinction, the possibility of a data: URI, the fallback to /favicon.ico, and the explicit note that existence is never verified. This is exactly the extra context the annotations cannot convey.

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?

Dense but front-loaded: it leads with the return value, then the mechanism, then the fallback, then the usage caveat. Every sentence carries distinct information with no 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?

With no output schema, the description fully compensates by describing the return shape (URL plus source: declared/default and a note) and the failure mode. Nothing an agent needs to call and interpret it 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?

Only one parameter (domain) with 100% schema description coverage, so the schema already documents it. The description adds no syntax or format detail beyond the example already in the schema, so baseline 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+resource: returns the favicon URL a website declares, and explains the resolution mechanism (fetch homepage, take first <link rel='icon'> href). An agent immediately understands it differs from link_metadata or url_clean siblings.

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?

'Use it to display a site icon; it does not download or validate the image' gives a clear intended purpose and an explicit exclusion (no download/validation). It doesn't name a sibling alternative when one might overlap, but the when-to-use context is unambiguous.

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