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

Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=false). The description adds genuinely non-obvious behavior: the absence of a notification is not evidence of failure, which is a subtle semantic the annotations cannot express. It stops short of describing what a notification object contains or how failures are represented.

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 tight sentences: what it returns, the failure-detection use case, then the success-confirmation alternative. No filler, and the negative case is placed immediately after the positive use case for contrast.

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?

No output schema exists, and the description does not say what a notification record looks like (fields, error text, recipe references), which an agent inspecting failures would want. Everything else needed to decide whether and how to call it is present.

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 100%, with limit and session_token fully documented including the Authorization header alternative. The description adds nothing about parameters, so the 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 resource (the connected account's recent notifications) and its ordering (newest first), plus the concrete question it answers. It is instantly distinguishable from siblings like search_recipes or check_agent_connection.

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 names when to use it (to detect a failed or split import_recipe_from_video) and, crucially, when NOT to trust it (a plain successful import sends no notification by design). It then routes the agent to the correct alternative, search_recipes(mine=True), with the caveat of waiting first.

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