Fds apply text

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

Annotations declare destructive/non-idempotent, but the description adds substantial behavior beyond them: only changed sections are applied, untouched sections retain app metadata, changed sections are replaced by parsed values, dryRun defaults to true, and nothing changes on a parse error (atomicity). This is exactly the kind of write-operation context annotations cannot express.

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 core action and workflow, then mode and filter behavior, with each sentence carrying distinct information (comparison semantics, dryRun, sections, error handling). The trailing [bulc-mcp rules] token injection is extraneous noise but the core text is tight.

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 3-parameter mutation tool with no output schema and full schema coverage, the description supplies the workflow, the diff semantics, the filter, and the failure mode, so an agent can invoke it correctly. Return-shape detail is not needed given no output schema; remaining gap is only the absence of explicit alternatives to the granular child tools.

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 baseline is 3, but the description adds meaning: dryRun default is true and behaves as a report-only mode, and 'sections limits which top-level sections may change' explains the parameter's effect on the operation rather than just its type.

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 ('Apply') and resource ('edited FDS deck to the project') and describes the exact mechanism: parse the complete .fds text and section-by-section compare with the current model. It also anchors the workflow to the sibling tool preview_fds, so it is distinguishable from the many granular mutation tools (add_obstacle, update_vent, etc.).

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?

Explicitly names the workflow and alternative: 'start from preview_fds, edit, send back', and explains the safe default (dryRun=true reports only). It does not explicitly state when NOT to use this bulk path versus the granular per-object siblings, but the intended context is unambiguous.

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