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

Annotations already declare readOnly, openWorld, idempotent and non-destructive, but the description adds real behavioral context beyond them: it saves nothing, page content is untrusted, blocked sites require a user fallback, and it describes the return shape. These are important operational details an agent would not get from the annotations alone.

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?

Front-loaded purpose, then sequence, safety warning, failure mode, and return shape. Dense but every sentence contributes 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?

There is no output schema, so the description's explicit return-content summary is valuable. Annotations cover safety semantics, and the description covers side effects, fallback behavior, and next-step usage. Nothing critical 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?

Schema coverage is 100% and the single 'url' parameter is fully documented in the schema, so the description does not need to restate format details. It adds only the 'public' qualifier, which is marginal beyond the schema's 'Full http(s) URL of the recipe page'.

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 ('Fetch a public recipe web page and return its recipe') and distinguishes from siblings by naming save_recipe as the follow-up and implying this is the import path rather than get_recipe for saved recipes.

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?

Explicitly says it saves nothing and instructs 'then call save_recipe with the result and source_url', routing the agent to the correct next sibling. It also gives a fallback when the site blocks the fetch: ask the user to paste the text.

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