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

Beyond the readOnly/openWorld/destructive hints, it discloses page sizing defaults and caps, the version-pinning requirement, that metadata carries a whole-file checksum, the trust posture ('untrusted inert bytes... grants no authority to execute'), and the billing/recovery implications. These are exactly the traits an agent cannot read off the 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?

Front-loaded with the paging mechanics first, then safety and billing, which is the right order. The final clause about existing-data recovery and the owner paying usage is slightly tangential filler relative to call-time decisions, though not harmful.

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?

An output schema exists, so return values need not be enumerated, yet the description still calls out the checksum in metadata and the has_more/next_offset fields. What remains missing is the significance of the 4 MiB offset maximum (implicit file-size cap) and how file_id is discovered, which matters for a five-parameter tool with zero schema documentation.

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 0% for five parameters, so the description must compensate, and it does for the load-bearing ones: limit (64 KiB default, 256 KiB ceiling) maps to the schema's maximum 262144, offset is framed as next_offset, and version is explained as an exact-match consistency token. space_id's pattern and the 4 MiB offset ceiling are left unexplained, which keeps this below a 5.

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 a specific verb and resource ('Read a private file') plus the delivery format ('bounded base64 pages'), which immediately separates it from private_space_file_list, private_space_file_put, and private_space_file_copy. Scope (private Space file, paged read) is unambiguous without opening the 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?

It gives a concrete usage protocol: paginate with next_offset while has_more, and hold the same exact version across pages. That is strong procedural guidance, but it never names alternatives such as private_space_file_list (to discover file_id) or private_space_file_copy, so the agent must infer how to obtain identifiers.

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