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

Annotations only say it is non-destructive and non-readonly; the description goes much further by disclosing the review-queue lifecycle (human accepts/rejects change by change), the hard rule that ops without a quote are refused, the idempotent replay semantics returning an existing proposal, and that nothing is written to the schema.

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 contract is front-loaded in the first sentence and each subsequent sentence adds a distinct operational fact (queue, precondition reads, quote rule, reviewUrl). The heavy capitalization for emphasis and mid-sentence asides make it denser than necessary, but no sentence is filler.

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 complex 6-param, nested-object tool with no output schema, the description covers the mutation lifecycle, requires-state explanation, and the returned reviewUrl plus the follow-up reader. The per-op vocabulary is left to the schema, which handles it, so the remaining gap is small.

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 already 83%, so the schema documents nearly all parameters itself; the description largely restates the quote/identifier requirement ('each with its identifier and the QUOTE') rather than adding new format or constraint detail beyond what the schema provides.

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?

The opening clause states exactly what the tool does and what it does not: 'PROPOSES changes without applying them.' The verb+resource ('propose_changes') is disambiguated from the many write siblings (add_cell, apply_batch, etc.) by the explicit 'nothing is ever written to the schema' scope statement.

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 names the upstream reads ('get_schema_overview, search_cells') and the downstream read-back tool ('get_proposal') and the 'meeting notes → graph update' flow, giving clear when-to-use context. It stops short of explicitly contrasting itself with the sibling that actually applies changes (apply_batch), so the alternative is only implied.

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