Save a recipe you already have

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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description adds useful context beyond that: the ingredient list must be complete with quantities, steps are required, and a submitted photo URL must be real because the server verifies and drops dead links. It still says nothing about duplicate handling (same title already saved) or what happens to an existing recipe with the same name, which is the main behavioral uncertainty for a create tool.

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?

Purpose is front-loaded in the first clause, followed by the qualifying scenarios and then the required-input guidance; no sentence is filler. It is a single dense paragraph, which is acceptable but slightly harder to scan than a short bulleted split would be.

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?

An output schema exists, so return values need no explanation, and annotations cover the mutation/safety profile. For a nine-parameter create tool the description covers purpose, triggers, and the two data-quality-critical inputs (ingredients with quantities, real image URL); the remaining gap is duplicate/overwrite behavior.

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 only 11%, so the description has to compensate, and it does for the important fields: it explains that ingredients need quantities and steps must be supplied, that source_url and image_url are wanted when available, and that favorite is an optional flag. It leaves tags, servings, description and the title field unaddressed, so a few of the nine parameters still rely on bare schema type information.

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 gives a specific verb and resource ("Save a recipe to the library") and then enumerates three concrete situations the tool covers: a recipe read in the browser where import_recipe is blocked or the page has no markup, an owner-dictated recipe, and one the agent wrote itself. It explicitly distinguishes this from import_recipe, so an agent can pick without opening the schema.

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?

It names the alternative ("when a site blocks import_recipe or has no recipe markup") and the other qualifying contexts (dictated, self-authored), which is close to explicit when/when-not guidance. It stops short of differentiating from the other write-path siblings in the list, notably add_library_recipe and update_recipe, so an agent could still hesitate between those.

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