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

With zero annotations, the description carries the full burden of behavioral disclosure. It does disclose a genuine behavioral trait — that the tool searches the materials database by name rather than requiring exact IDs — which is useful. However, for a mutation tool it stays silent on important behaviors: whether adding a duplicate material is an error or a no-op, whether changes are persisted immediately, how multi-match or zero-match searches are handled, and what the response contains. Credit for the search semantics, but an agent can't predict the tool's behavior on edge cases.

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 tight sentences: the first front-loads the purpose, the second carries the key behavioral trait. Every word earns its place and there is zero fluff or redundancy with the schema. A third sentence on error/return behavior would have earned a 5, but as written it's efficient and well-ordered.

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 tool with 5 params (3 required), no output schema, and no annotations, the description is functional but not comprehensive. It communicates the essential flow — add a material, searchable by name — and the schema carries parameter documentation. However, for a mutating operation, the lack of any stated expectation about return values, idempotency, or validation behavior (e.g., what if materialQuery has zero matches?) leaves an agent without enough to anticipate failures. It's adequate for the happy path but falls short of what a well-rounded mutation tool description should cover.

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%, with each of the five parameters already well-explained (e.g., modelId references create_cost_model, qty and scrapFactor state their defaults, materialQuery has examples). Per the rubric, a baseline of 3 applies. The description's 'Searches the materials database by name query — no need for exact IDs' does add marginal meaning by confirming materialQuery is fuzzy-match, not an identifier — a useful clarification that justifies the baseline rather than below. But there's no additional parameter semantics in the description that goes beyond what the schema already says.

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?

Uses a specific verb+resource ('Add a material (BOM line) to an existing cost model') and adds the search-by-name behavioral differentiator, which cleanly distances it from the exact-ID workflow an agent might assume. Together with the sibling name add_process_to_model, an agent can immediately tell which tool handles materials vs. processes. The 'no need for exact IDs' clause is the kind of behavioral detail that makes the purpose unambiguous.

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 intended use case — adding a material to a model by name — is implied and correct, but the description never explicitly states when to prefer this over related siblings like add_process_to_model or search_materials, nor does it mention any when-not-to-use conditions. An agent could infer 'materials go here, processes go to the other one,' but that inference rides on sibling tool names rather than anything the description states. There is also no mention of what happens if the materialQuery returns no results or multiple results, which is a meaningful usage gap for a fuzzy-search mutation.

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