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

The annotations (readOnlyHint: true, idempotentHint: true) already establish safety. The description adds materially by disclosing the matching heuristic (text-based matching, not identity — near-misses count, while synonym pairs like courgette/zucchini may fail) and the partial-match fallback behavior (returns closest partial matches rather than erroring). This is exactly the kind of behavioral nuance an agent needs to interpret results correctly. No contradiction with annotations.

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 cover purpose, matching heuristic, and responsibility boundary without redundancy. The first sentence is front-loaded with the core function. However, the second sentence's caveat chain ('a near-miss on the name still counts, but...') is slightly convoluted to parse, though each clause earns its place.

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?

For a read-only, idempotent ranking tool, the description comprehensively covers what the agent needs: ranking logic, matching semantics, partial-match behavior, and caller responsibility. The only minor gap is no description of the return format, but since there's no output schema and the tool is non-destructive, the cost of this gap is low. The description fully compensates for the lack of enum constraints or nested complexity.

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% — both `ingredients` (with example) and `limit` (with default and bounds) are well-documented in the schema itself. The description's matching semantics do enrich how one understands the `ingredients` param, but this is incidental rather than a direct param explanation. Since the schema carries the load, the baseline of 3 is appropriate.

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 clearly states a specific verb ('rank'), resource ('recipes at recipes-daily.com'), and ranking criterion ('by how many of them each one uses'). It goes beyond a generic statement by scoping the ranking behavior and how the tool communicates missing ingredients, which distinguishes it meaningfully from the sibling tool search_recipes.

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 description gives clear context on when to use this tool (when you have a list of ingredients and want recipes ranked by coverage) and explicitly states what it is NOT ('not a substitution finder') and that the caller is responsible for substitution decisions. It stops short of explicitly naming the sibling alternative, but the boundary is well-drawn.

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