excel_write_csv

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

Annotations only supply the generic write profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false); the description adds real operational context: env-var gating, refusal to follow symlinks, output-root confinement, and formula-looking text being prefixed. These are meaningful behavioral traits an agent could not infer from structured fields. It stops short of saying what happens on an existing file or a failed write.

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?

Four short, front-loaded sentences with no filler; the primary action comes first, then gating, then safety constraints. Every sentence carries distinct information.

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?

The existence of an output schema means return values need not be described, and the safety/gating story is well covered. But for a 12-parameter mutation tool with 0% schema description coverage, the complete absence of parameter meaning leaves a substantial gap an agent cannot close elsewhere.

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% across 12 parameters, so the schema supplies names and defaults but no meaning. The description touches only formula handling (loosely related to include_formulas) and says nothing about sheet, sheet_index, table_index, offset, max_rows, header_row, decimal, normalize_units, or overwrite — the parameters that determine what actually gets written.

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 (write) and resource (the cleaned table) plus the target formats and the sandboxed location (EXCEL_OUTPUT_ROOTS). This implicitly separates it from the five read-only siblings, though it never explicitly contrasts with them. Minor naming mismatch: the tool is named excel_write_csv but the description covers both .csv and .json.

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 one hard precondition — the tool is disabled unless EXCEL_ALLOW_WRITE=1 — which is genuinely actionable. However, it offers no guidance on when to choose .csv vs .json, and no comparison against any alternative writing path. Usage is implied rather than directed.

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