audit_deck

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

With no annotations, the description carries the full burden and does so: it declares read-only/non-executing behavior, explains that parsing is plain text, discloses the *INCLUDE traversal restriction ('only inside the allowed folders'), and states the return shape (findings with severity/card/field/message plus a compact summary). These are exactly the behavioral traits an agent cannot get from the schema.

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-loaded with the one-line identity and read-only guarantee, then a dense but information-bearing checklist of checks. It is a long run-on paragraph where bullets or a sentence break before 'Args:' and 'Returns' would aid scanning, but no sentence is filler.

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?

An output schema exists, so the brief description of findings/summary is a bonus rather than a requirement. The pre-solve audit scope, the include-folder restriction, and the unverified-citation caveat together make it complete enough to call correctly; only the 'allowed folders' configuration source and deck_path expectations remain unspecified.

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 0%, so the description must compensate; it partly does by glossing include_children as 'follow *INCLUDE files', which matches the schema default of true and adds real meaning. deck_path is left entirely unexplained (accepted formats, relative vs. absolute, whether it must be a directory or .k file), so the semantic gap is only half closed.

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?

Names a specific verb and resource ('read-only audit of an LS-DYNA keyword deck') and enumerates exactly what it checks (card families, duplicate ids, dangling references, format problems, unit guess, end time vs. output intervals, Workbench defaults). An agent knows precisely what the tool produces; however it never names the closest sibling (presolve_check, scan_keyword_file, compare_decks), so differentiation is by inference only.

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 phrase 'before it is solved' plus '(plain text parsing, nothing is executed)' gives clear timing/context for when to reach for it. There is no explicit when-not guidance or pointer to the alternative tools for post-solve or comparative checks, so a routing decision against presolve_check is left to the agent.

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