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

Annotations only cover the safe-read profile (readOnly, idempotent, non-destructive), and the description adds substantial behavior on top: matching is case/space/hyphen insensitive, short codes trigger prefix expansion, specifications such as ASTM A240 fan out to every citing material, and each row carries a note plus an exactness flag. It also warns that a "nearest equivalent" note is the source's own hedge and should not be treated as grade equivalence — a genuinely non-obvious behavioral caveat.

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?

Purpose is front-loaded in the first sentence, and every subsequent sentence carries a distinct, load-bearing fact (input tolerance, row shape, spec fan-out, equivalence caveat). The enumeration of code systems is dense but not redundant, keeping it just short of wasteful.

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?

With no output schema and a single parameter, the description carries the return-value burden and does so fully: it names the four row fields (system, code, note, exact flag) and explains the two non-obvious cardinality cases (prefix expansion and specification-driven multi-material results). Nothing an agent needs to call this correctly or interpret the result is missing.

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% and the single `code` parameter is already documented with examples, so the baseline is 3. The description adds meaning beyond the schema by listing the full set of accepted governing systems and by specifying the normalization rules (case, spaces, hyphens ignored) and the 60-char scale implied by prefix matching.

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?

Opens with a precise framing ("Which material a code names") and enumerates exactly which identifier systems it accepts, with concrete examples. An agent can tell this is a designation-to-material resolver rather than a keyword search, though it never names the sibling tools (search_materials, find_materials) it sits beside.

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?

Usage context is implied through the accepted input forms (UNS, EN, DIN, JIS, AISI/SAE, ASTM/AMS, trade names) and the note that a short code lists codes that start with it, which tells an agent when the tool fits. However, there is no explicit when-not-use rule or pointer to alternatives such as search_materials or get_material for follow-up.

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