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

With no annotations, the description must carry the behavioral load. It discloses cursor-pagination, the returned fields, and that encrypted rooms are unsupported. However, it does not explicitly state the operation is read-only (though implied), lacks error behavior mention, and doesn't mention auth requirements beyond the schema's connection parameter – leaving some gaps.

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?

Two sentences with zero filler. The primary purpose is front-loaded, followed by scoping, return behavior, and a usage hint. Well-structured and efficient.

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?

Without an output schema, it explains return values (IDs, descriptions, revisions, private links) and mentions the encrypted-room limitation. It lacks explicit error handling or pagination mechanics details, but for a list/directory tool this is sufficient. The workflow suggestion to use page_get adds practical completeness.

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 coverage is 80% (4 of 5 params described). The description adds meaning beyond schema: it clarifies that 'query' accepts title/description/exact ID, that channel_id is optional and scope-based, and that pagination uses a cursor. It doesn't elaborate on limit or connection, but those are adequately covered 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?

The description opens with 'Discover shared HTML pages' – a specific verb and resource. It details the search capability (titles/descriptions/exact IDs) and what is returned (IDs, descriptions, revisions, private links), clearly distinguishing it from siblings like page_get (retrieve single page) and page_create/page_update.

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?

Provides explicit guidance: 'omit channel_id to search all accessible standard rooms' gives scope definition, and 'Read relevant pages with page_get before contributing' establishes a workflow. It doesn't explicitly mention alternatives or when not to use, but the context is clear enough.

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