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

Annotations already declare readOnly=false, destructive=false, idempotent=false and openWorld=false, yet the description adds two things they cannot: every call creates a NEW recipe (reinforcing non-idempotency) and the result is private to this user in searches and saves. It also discloses that the server performs extraction server-side rather than the agent. No contradiction with the declared hints.

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 sentences, each doing distinct work: input modalities first, the markup/source_url mechanics second, the privacy consequence last. No repetition of the schema or the annotations, and 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?

An output schema exists, so return values need not be described, and the description covers privacy, extraction behavior, and the two viable input paths. With 8 parameters at 63% schema coverage, a few fields (yield, description, total_minutes) rely entirely on their names, leaving a small completeness gap for what is otherwise a rich, well-scoped definition.

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 a middling 63% with 8 parameters, but the description adds real meaning beyond the schema: it explains that markup (raw HTML or just the JSON-LD block) plus source_url triggers server-side extraction, and explicitly says the other fields 'can stay empty' in that path. Undocumented parameters like yield and total_minutes get no narrative help, keeping this below a 5.

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 ('Add a recipe the user supplies themselves') and scopes the input modalities: pasted, dictated, family recipe, or a pointed-at web page. Together with the title 'Upload a private recipe' and the closing 'creates a new private recipe, visible only to this user', an agent can separate this from save_recipe and share_recipe without opening a 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?

Enumerates the situations that select this tool (user-supplied text, dictation, family recipe, web page) and gives concrete direction for the web-page case: pass raw HTML or the JSON-LD as markup with source_url. It stops short of naming alternatives or stating when NOT to use it versus save_recipe, so it is clear context without explicit exclusions.

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