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

Adds substantial behavior beyond the readOnly/idempotent annotations: per-call character cap, offset/limit paging with next_offset, sha256 and byte-length return values, truncation behavior for binary/over-cap files, and the binding semantics of header lines. An agent knows exactly what will happen on repeated or partial reads.

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?

Dense but purposeful: the first clause names the operation, the middle explains limits and output, and the final sentence gives operational guidance for paging and record-binding. No filler; every sentence adds information needed to call or interpret the tool correctly.

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?

Even without an output schema, the description covers the return payload, paging mechanics, sha256/byte-length metadata, binary/over-cap edge cases, and the reviewer-binding semantics. An agent has enough contextual detail to invoke the tool and handle partial or empty results correctly.

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 adds useful semantic context by framing limit/offset as paging over characters, explaining that truncated reads return next_offset, and emphasizing that path must refer to the exact build-listed artifact. This goes slightly beyond the bare schema definitions.

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 action ('Read one file'), a precise resource ('stored build bundle'), and the selection keys ('by build_ref and path'). It also differentiates itself from a working-tree read and from the related tool tascan_get_build, so an agent can tell exactly what this tool is for.

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 clear context: this is the read tier for exact executor-produced build artifacts and is what the independent reviewer reads. It implicitly excludes working-tree reads and other list-style build tools, though it does not spell out a formal when-to-use vs. when-not-to-use against each alternative.

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