build_model

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

With no annotations provided, the description carries the full burden. It discloses that the tool runs a single engine, iteratively re-estimates with intervention additions, stops after 'clean diagnosis or max_rounds', and 'Always returns parameters + residual diagnosis figure; DCD/MEG at the end.' It also reveals side effects: writes to output_path and records to guion_path. Missing are failure modes, performance expectations (except run_meg slow), and explicit permission needs, but overall it is fairly transparent.

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 description is well-structured: a clear opening purpose, a bulleted mode explanation, a 'returns' line, and a parameter list. It is longer than average, but the length is justified by 15 parameters and the need to explain two modes. The combined 'd, D' line introduces slight ambiguity, preventing a perfect score.

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?

Given the tool's complexity (15 params, no annotations, no output schema), the description is highly complete. It explains the pipeline flow, mode selection, parameter sentinels, and return values, and even sequences it after guided_identification. Minor gaps: the d/D distinction is not explicit, and no alternatives or exclusions are mentioned, which would push it to a 5.

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?

The input schema has 0% description coverage, but the description's parameter section explains all 15 parameters with sentinel meanings (e.g., '-1 = let the heuristic decide'), allowed values (lam 0/0.5/1, decision A/B1/B2), and roles (inp_path source, output_path final .inp, guion fields for recording). This far exceeds the schema's bare type/default information and fully compensates for the lack of schema descriptions.

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?

The description clearly states the tool runs a 'Box-Jenkins-Treadway pipeline for a single series' and details the iterative process: deciding the spec, estimating, adding interventions for outliers, and re-estimating until clean or max_rounds. It distinguishes modes (autonomous vs guided) and references 'guided_identification' as a precursor, which differentiates it from siblings. The verb 'build' and resource 'model' are specific.

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 description gives explicit guidance: use guided mode 'after guided_identification to run the build with the confirmed spec while the outlier cycle proceeds automatically.' It also explains when the heuristic decides (autonomous) vs when analyst choices are honored (guided). However, it does not name alternative tools or state when not to use this tool, which would make it a 5.

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