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

Annotations already cover safety (readOnly, idempotent, closed-world), yet the description adds real behavioral detail beyond them: a miss returns nearest pages, URL + '.md' yields markdown, and blocks:true returns stored blocks with ids plus full metadata. It also explains the read-before-edit workflow and the version/baseVersion contract, which nothing else discloses.

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?

Front-loads the return shape, then addressing, then the batch alternative and edit workflow — a sensible order with no filler sentences. It is dense and runs longer than most definitions, but nearly every clause carries load; slightly tighter phrasing would reach a 5.

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?

No output schema exists, and the description compensates by describing the returned fields, the blocks variant's structure, and the miss response. For a 4-parameter read tool with full annotation coverage, an agent has everything needed to call it correctly and to recover from failures.

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 100%, so baseline is 3, but the description adds meaning the schema lacks: it clarifies that path values must be exactly the path or url a listing returns and that a category's path reads its hub, and it expands blocks:true into the full return shape and editing workflow. That is substantive value over the schema's one-line descriptions.

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 and resource: reads one page 'in full: its text, version, update date and metadata.' Immediately distinguishes it from get_pages (batch) and implicitly from list_pages/search_wiki by naming the sibling it is not.

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?

Explicit routing: 'For 2 to 20 pages call get_pages, one round trip rather than N.' Gives addressing rules (path preferred over tagPath+slug, not a title, category path reads its hub) and the recovery path for a wrong guess. When-to-use and alternatives are both stated.

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