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

Annotations already declare readOnly/idempotent/destructive=false, yet the description adds substantial value beyond them: the returned etag to use as ifMatch, guarded pointers invisible to this token, the ITEM_VERSION_NOT_RETAINED error path, and request counting (1 request, +1 first use of a list unless get_list was called). This is rich operational context an agent needs.

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-loaded with what it returns (metadata/data) before behavioral details, and every sentence carries information. Some phrasing is dense and slightly awkward ('the plan keeps fails'), costing a point but not impeding comprehension.

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?

With an output schema present, return values needn't be described, and the description still covers the key behaviors: versioning limits, etag/guarded semantics, and request cost. For a 7-parameter read tool this is largely complete, with only minor gaps around the includeData/includeGuarded toggles.

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 the baseline is 3; the description still earns extra by clarifying pointer-vs-path intent and the version-retention constraint that governs the 'version' parameter. It adds meaning beyond the schema's own field docs, though it does not re-explain includeData/includeGuarded.

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+resource and enumerates the scope variations it supports: metadata and data, part of data via pointer or path, current or older version. An agent can immediately tell this is a point-read of a single item, distinct from list_items/search_items, without opening a 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 explicit routing for the failure case ('a version older than the plan keeps fails... read it from its event with get_event instead') and notes the get_list interaction for request cost. It lacks broader when-not guidance versus siblings like search_items or list_items, but the conditional alternative is clearly stated.

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