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

Annotations only declare non-read-only, open-world, non-idempotent, non-destructive. The description goes well beyond them: it names the return shape { accepted, url }, discloses that the call validates the link and checks the recipe limit, and warns that the operation is incomplete until two further calls are made. That partial-completion trait is the most important behavioral fact and is not derivable from annotations.

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-loads the action, then the trigger, then the return and the critical non-completion warning, ending with the docs pointer. Every sentence carries information, though the multi-step follow-up instructions and URL push it longer than a minimal definition.

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, but the description supplies the return shape, the precondition checks, the multi-call completion path, and a documentation link. For a non-idempotent three-step workflow, nothing an agent needs to avoid a false 'saved' report 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 param is described only as 'The recipe link,' so the baseline would be 3. The description adds real semantic value by constraining the valid input domain to Instagram/TikTok posts and food blogs, which tells the agent what kind of URL will be accepted.

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 ('Queue a recipe link to import') and enumerates the accepted sources (Instagram, TikTok, food blog). It also sharply scopes the tool as a start/queue step rather than the import itself, so the agent can distinguish it from the concept of a completed save.

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?

Gives an explicit trigger ('Use this when they share a link and want it in their cookbook') and an explicit non-outcome ('IT DOES NOT IMPORT THE RECIPE BY ITSELF — do not report it as saved on this result alone'), plus the exact follow-up sequence. This is when-to-use, when-not-to-claim success, and the alternative path all in one.

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