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

Annotations already declare readOnly, idempotent and closed-world, so the basics are covered; the description adds cost/allowance behavior ('priced like a decode, on the same free allowance'), determinism ('no LLM'), and provenance labelling ('seen standard' vs 'seen draft'). It also discloses what each row contains and that the ACSS build is supplied alongside the standard row, which goes well beyond the annotations. It stops short of describing how multiple matches or pagination behave when a code hits many country tables.

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 core purpose is front-loaded, but the body is a single run-on construction with deeply nested parentheses and clause citations, making it hard to scan for the actionable parts. The information is largely earned, but it would be materially clearer split into separate sentences for input forms, return content and routing.

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, the description still enumerates the returned fields (stranding, areas, diameters, mass, rated tensile strength, d.c. resistance at 20 °C, tolerances, lay) plus the ACSS build and its draft provenance. Input forms, defaults, and the sibling to use instead are all covered, so an agent has everything needed to call it correctly.

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, but the description adds relational meaning the schema does not: 'table' with 'row' selects one line of that table, 'table' alone answers every row, and 'core' defaults to ST6A or the ACSS code's own core wire. That clarifies how the four parameters combine rather than merely restating them.

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?

Specific verb+resource: 'Look up a bare overhead line conductor', qualified by conductor families (AAC, AAAC, ACSR, ACSR/AW) and the governing standards (EN 50182:2001 4.5, FprEN 50540 clause 4). It explicitly distinguishes itself from decode_cable_code for insulated cables, so an agent can separate it from that sibling without opening either schema.

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?

States the two intended uses ('read an overhead conductor code or compare one country's table with another's') and names the alternative for the adjacent case ('for insulated cables use decode_cable_code'). The three accepted input forms (code, ACSS code, Annex F table) are each tied to their own condition of use.

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