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

Annotations already cover the read-only/idempotent/non-destructive profile, yet the description adds substantial context beyond them: read page.cells[].value not rawValue, email/phone remain arrays, phone normalization rules, evidence.applied=false means an unapplied proposal, null evidence/empty sources yield no citation, and external source text is untrusted data never instructions (a prompt-injection warning). This is rich behavioral disclosure an agent could not infer from the annotations.

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?

The core purpose is front-loaded and every sentence is substantive rather than filler. It is dense and hops between value semantics, evidence rules, pagination, and versioning, which makes it a long read, but no sentence is clearly expendable.

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, so return-value documentation is not strictly required, yet the description usefully clarifies the tricky value/rawValue and evidence semantics anyway. Given the tool's complexity, the main gap is the unexplained query sub-fields, but the agent has enough to call it correctly.

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 must carry the load. It explains some parameters well (snapshotRevision to reuse as expectedRevision, nextCursor as opaque, projecting only needed columnIds, expectedVersion 0 vs entityVersion for writes), but the nested query fields q, sort, filters, history, version, pageSize, direction and focusRowId are never given meaning. It compensates partially rather than fully for a deeply nested 4-parameter 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 and resource plus scope: 'Read one revision-consistent, bounded page of rows and sparse typed cells.' It further distinguishes itself from siblings by naming sheets_aggregate for counts/statistics and positioning itself as the tool for verifying saved values, so an agent can route without opening another schema.

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 an explicit alternative ('Use sheets_aggregate for ordinary counts/statistics instead of scanning pages') and a usage directive ('For enrichment progress read values and presence, never sleep-wait inside execute'), plus how to paginate via nextCursor. It stops short of full when-not coverage (e.g., when to prefer sheets_get or sheets_search_rows over a full page scan), so it is strong but not exhaustive.

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