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

With no annotations, the description carries the full burden and does so richly: conflict means no published content changed and change_id retains the proposal, retries require a new key/base revision, blind overwrites are forbidden, and metadata-only edits are supported. It also discloses that patches and html replacement are mutually exclusive. These are meaningful behavioral traits not otherwise visible in schema or 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 description is dense but every sentence earns its place: core action, edit-mode strategy, metadata-only support, conflict behavior, reconciliation workflow, overwrite warning, and restore path. It is front-loaded with the primary action and mode preference, and contains no filler or redundant prose.

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 description, combined with 80% schema coverage, gives an agent enough to invoke the tool safely: base_revision usage, idempotency rules, conflict retry behavior, and restore semantics. The connection credential caveat is handled in the schema. The only real gap is the absence of any description of the successful return shape, though mentions of status=conflict and change_id partially mitigate this.

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 80%, so the structured data already documents most parameters. The description adds strategic meaning beyond the schema: prefer sequential exact patches over html replacement, never combine patches and html, support metadata-only edits, and retry with a NEW idempotency key/base revision. This enhances rather than merely repeats 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?

The description states a specific action and resource: 'Contribute to a shared page using the base_revision you read,' and clarifies the update modes (patches, html replacement, metadata-only). This clearly signals an update to an existing page and distinguishes it from read-only siblings like page_get and page_history. It stops short of 5 because it never explicitly differentiates from page_create for new-page creation.

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?

The description gives strong operational guidance: prefer sequential exact patches, use html replacement alternatively but never both, and on conflict read page_get/page_history then retry with a NEW key/base revision. It also explains the restore workflow of submitting an old revision against the current one. It does not explicitly exclude alternatives such as page_create, leaving some tool-selection guidance implicit.

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