Spr export results

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

Annotations already mark this as a non-read-only, non-idempotent write, and the description adds real context beyond them: files are written to the local path, csv uses UTF-8 BOM, zip creates one archive per format, fhcDraft adds .FHC/.PDT drafts needing external verification, and recalc-vs-reuse behavior. The round-trip contract with spr_import_fhc_bundle is an extra disclosure the annotations cannot carry.

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?

A single dense paragraph that front-loads the primary action (write results to files) before the option breakdown. The volume of format detail is justified by a 9-parameter, multi-artifact tool, though the run-on structure is slightly heavy.

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?

For a 9-parameter, no-output-schema file-writing tool, the description specifies formats, defaults, recalculation behavior, the FHC draft caveat, and the import round-trip. Nothing an agent needs to invoke it correctly appears 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%, so the baseline is 3, but the description adds substantial meaning: what each format value actually emits (csv = 5 tables, fhc = 7 CSV sets, both), the scenario syntax 'all' | 'zone:<zone>', and supply-vs-design semantics. projectName (CHID default) and slopeMode are left to the schema, slightly limiting the add.

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 ('Write the sprinkler / water-spray design results to files') and enumerates the exact artifacts per format, so the agent knows precisely what is produced. It is clearly distinguishable from spr_get_results (in-memory retrieval) and spr_import_fhc_bundle (the read-back counterpart, which it names).

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?

Gives defaults and conditions for the key switches (scenario default = governing scenario, at default = supply, format default = both) and notes it uses current results or recalculates. It also flags the FHC round-trip via spr_import_fhc_bundle, but does not explicitly state when to prefer this over spr_get_results or other result tools.

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