validate_input

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

With no annotations, the description carries the burden and does well: it discloses that the deeper mode invokes an external process (`sss2 -noplot -norun`) and that this only happens 'when the executable is available', which is real environmental/behavioral context. It does not state that validation is non-mutating or how long the external run may take, but the key conditional behavior is surfaced.

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 dense but front-loaded sentences: the core validation purpose and its checks come first, with the optional deep mode second. No filler, though the first sentence packs a long enumeration that could be trimmed slightly.

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 return values need not be described, and the check inventory is thorough. The gap is the unexplained text/input parameter pair and the undefined intermediate levels, which an agent needs to choose arguments correctly for a 4-param tool.

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 explain all four parameters. It partially covers level and run_norun, but the critical distinction between the `text` and `input` parameters (raw text vs. file path?) is left entirely unexplained, and the meaning of level values below 3 is absent.

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?

States a specific verb and resource ('statically validate a Serpent input file') and enumerates the actual checks performed (known cards/options, duplicate names, undefined references, unit mixing, source/neutron-mode consistency). This clearly separates it from execution-oriented siblings like run and job_status, since it is explicitly static.

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?

It gives a concrete condition for the deeper mode ('level=3 (or run_norun=true) also runs sss2...'), which is useful routing within the tool. However, it never says when to reach for validate_input rather than run or get_reference, nor what levels 1 and 2 mean, so the when-to-use guidance is only implied.

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