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

Annotations already cover the safe-read profile, and the description still adds substantial behavioral context: counts cover the entire selected scope, offset/limit page newest-first, each runId maps to exactly one cell, null evidence or empty sources mean no citation. The billing semantics are especially valuable: settledCredits is the confirmed subtotal (never a quote), pending=true means accounting is incomplete even if the subtotal is zero, and only pending=false establishes a final total.

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?

Purpose is front-loaded in the first clause, and the remaining sentences are dense with load-bearing information rather than filler. It is long (roughly ten clauses) and shifts without signposting between scope, pagination, evidence, billing, and exclusions, but every sentence earns its place.

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, yet the description still explains the semantics of returned fields (evidence, sources, billing.settledCredits, billing.pending) which the schema alone could not convey. Combined with the scoping exclusions and pagination contract, an agent has enough to invoke and interpret the call correctly; only the sibling routing gap remains.

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 description coverage is 0%, so the description carries the burden and largely does: rowIds and rowRange intersect when both are supplied, null means unrestricted, and offset/limit page individual runs newest first. sheetId and columnIds are not described, but 'for a sheet' and 'counts by column' make them self-evident. Numeric bounds are left to the schema.

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?

Opens with a specific verb+resource+scope: 'Read current cell-run status and counts by column for a sheet, explicit row/column IDs, or a row range.' An agent knows exactly what it gets. However, it never names or contrasts with the many sibling status tools (enrichment_get, enrichment_list, sheets_get_enrichment_proposals), so disambiguation from siblings is left to inference.

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 offers one concrete routing rule ('Read saved values through sheets.query and distinguish unapplied proposals') and a scoping exclusion ('No batch IDs, staff diagnostics, paid work or replay'). But much of the guidance is about interpreting returned data rather than when to call this tool versus enrichment_get, enrichment_list, or sheets_get_enrichment_proposals. Usage is implied rather than explicit.

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