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

Annotations already cover the safe-read profile (readOnlyHint, openWorldHint=false), but the description adds genuine behavior: versions is 'Used only for this call, never stored' (a statelessness guarantee) and produces a compatibility section classifying each package as exact/compatible/mismatch/not in your project. It doesn't describe failure modes for an invalid or stale id, which keeps it from a 5.

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 core purpose and the return contents before the versions behavior, and every sentence carries information. The closing imperatives ('Adapt names and config to the user's project...') are useful downstream guidance but lengthen an already dense paragraph, costing a point.

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, so the description must describe the return value — and it does so concretely (files with byte-level hashes, pinned versions, commands, test receipt fields). Combined with the versions semantics and non-storage note, an agent has everything needed to invoke and interpret the call.

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 only 50% (the id property is undocumented in the schema), and the description compensates by explaining where ids come from. For versions it goes beyond the schema by naming the downstream effect (compatibility section with four outcome categories) and advising to 'Use the pinned versions together'. That is meaningful semantic value over the structured fields.

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+resource ('Get a full recipe by id') and enumerates exactly what the recipe contains (source/test files with sha256, pinned dependency versions, setup/test commands, test receipt). It also names the sibling that produces ids ('ids come from search_recipes'), so the agent can distinguish it from search_recipes and list_stacks without opening another 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?

The id provenance ('ids come from search_recipes') gives clear routing: call search_recipes first, then get_recipe. 'Optional but recommended' for versions tells the agent when to bother passing it. What's missing is an explicit statement of when NOT to use this tool or how it relates to list_stacks, but the surrounding context is unambiguous.

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