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

Goes well beyond the readOnly/idempotent annotations: it defines the three verdicts, the evidence-strength ladder, the default result ordering and filtering, and the temperature-matching rule that silently excludes values. The exclusion of zero-data materials with a pointer to what_is_missing is exactly the kind of hidden behavior an agent needs disclosed.

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 essence in four words, then layers the verdict model, defaults, context knobs, and the exclusion rule in tight order. Dense but every clause carries information; nothing is repeated from the schema verbatim.

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, yet the description fully describes the return shape (per-material verdicts, per-constraint status, evidence level) and the default ordering. For a nested-parameter tool with a nontrivial result model, an agent has everything needed to call and interpret it.

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 100%, so the baseline is 3, and the description earns above that by framing context as "narrows which values count" and spelling out the at_temperature and flown_only exclusion semantics. It says nothing about the constraint object's operator, unit conversion, or value2 fields, leaving those entirely to the schema.

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?

"Requirements in, candidates out" plus the verdict model states a specific verb and resource that is clearly distinct from search_materials or get_material. The description also scopes what counts as a candidate (no materials with zero data), which an agent could not infer from the name alone.

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 states the default filter (passes and unknowns only, passes first) and routes the coverage question to what_is_missing. It does not, however, name search_materials as the alternative for name/keyword lookup, which is the most likely sibling confusion for a tool called "find".

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