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

The description discloses destructive behavior ('A null value clears a cell' and overwriting existing values), while the annotation destructiveHint=false declares the tool non-destructive. This is a direct contradiction, so the description fails behavioral transparency despite otherwise useful cost and limit details.

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?

Three compact sentences front-load the example and key constraints (limit, null behavior, cost) with no filler. Every sentence adds operational value.

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?

Covers the main operational details an agent needs: row-number targeting, null clearing, partial updates, row limit, and cost. It omits what happens when a row is not found or how row numbers should be obtained, though annotations otherwise cover the safety profile.

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 50%; the rows parameter is undocumented in the schema, but the description compensates with a format example, null-clearing semantics, the 500-row limit, and partial-update behavior. The table parameter is already documented in 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?

States a specific verb ('Change values') and resource ('rows'), with scope ('up to 500 rows by their row number') and an example. It distinguishes itself from deletion/insertion via row-number targeting, but does not explicitly name or contrast with siblings like rows_upsert.

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?

Usage is implied by the requirement to know row numbers and the note that only given columns change. However, there is no explicit when-to-use vs alternatives (e.g., rows_upsert), no preconditions, and no guidance on sourcing row numbers.

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