Material Select

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

Beyond the readOnlyHint annotation, the description discloses significant behavioral traits: the exact return shape, best-first ordering, and the edge case that an empty filter returns no candidates instead of the closest miss. It also defines the criteria key convention (min_<accessor>/max_<accessor>) with concrete examples. This gives an agent a precise expectation of the tool's behavior.

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?

The description is dense but efficiently organized: a one-sentence summary, then a compact breakdown of criteria keys, rank_by values, and return format. Every sentence adds new, useful information. The structure is front-loaded with the core concept and then technical details, making it easy to scan.

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?

The description is notably complete for a tool with no output schema and minimal parameter documentation: it covers criteria syntax, ranking options, return structure, ordering, and an edge case. Still, it does not explicitly mention the default rank_by or that criteria is optional (both in the schema), and the candidate score field is left unexplained. These are minor gaps given the overall richness.

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?

The input schema has 0% description coverage, and the description compensates well by fully enumerating rank_by options and explaining criteria keys with examples. It also documents the output fields, which helps infer parameter meaning. However, it does not list all possible accessors or specify value types/units, so parameter semantics are strong but not exhaustive.

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 'Ashby-style selection: filter the corpus, then rank survivors,' which clearly states the tool's purpose with a specific verb and resource. It further differentiates itself from material_get and material_list by describing a multi-step selection workflow. The rank_by and criteria key syntax reinforce the intended functionality.

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 clearly conveys when to use the tool: when you want to filter a corpus of materials by property thresholds and rank the survivors. However, it does not explicitly mention alternative tools like material_list or material_get or provide any exclusions for when not to use this tool. The context is clear but lacks explicit routing guidance.

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