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

The description frames the call as a passive inventory read ("List the account's recipes"), yet the annotations declare readOnlyHint=false and destructiveHint=true; an agent reconciling both cannot tell whether invoking this can mutate state. The description does add real behavioral context beyond annotations (newest-change-first ordering, included step counts, usage locations, exclusion of graphs), but the safety posture it implies is in direct tension with the supplied 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?

Two short sentences, both front-loaded: the primary capability and returned fields come first, the exclusion/routing hint second. No filler and nothing repeated from the schema.

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 the description covers the essentials of what the list contains. However, for a six-parameter tool with a five-parameter required session envelope, it omits pagination, the archived mode, and any caution relative to the destructive/openWorld annotations, leaving real gaps for correct invocation.

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 50%, and five of six parameters are required, so the description carries a real burden here. It says nothing about the pagination cursor ("after"), the archived toggle, or the session envelope parameters (work_id, request_key, expected_catalog_version), so it adds essentially no parameter meaning beyond the schema text.

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 opens with a specific verb and resource ("List the account's recipes") and immediately states the ordering and the two identifying fields returned (step count, where each is used). It also distinguishes itself from a named sibling by stating "Graphs are not included: use recipe_read for one." It does not differentiate from the similarly named non-native sibling list_recurring_recipes, which is the only remaining ambiguity.

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?

There is one explicit routing rule (need a graph -> recipe_read), which is genuine when-to-use guidance. Beyond that, nothing tells the agent when to pick this over recipe_plan_run, recipe_run, or list_recurring_recipes, nor how to handle paging or the archived variant, both of which exist as parameters.

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