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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds value by explaining the manifest is truncated at 12000 chars, computing build_ref (sha256 over the manifest), and that binary or over-cap files only store the sha. It also clarifies the discovery semantics, which goes beyond annotations. No contradiction.

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?

The description is a single, dense paragraph that packs essential information: purpose, content, computation, truncation, and sibling distinction. Every sentence adds value, front-loading the semantic difference from file reads. No fluff or repetition.

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?

Given the tool's single parameter, clear annotations (read-only, idempotent), and that the output schema is not provided (but the description describes what the manifest contains), this is complete. An agent can call it correctly, understand what it returns, and know to use tascan_get_build_file for file content. The truncation limit and read semantics are stated.

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 100%, so the schema already documents build_ref's format (sha256:<64 hex>). The description adds context that build_ref is a SHA256 over the manifest and how to obtain it (from tascan_get_task or tascan_get_cycle_report), which is additional meaning beyond the schema. Slight deduction for not fully detailing the manifest's structure beyond what's listed, but it's adequate for a single parameter.

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 clearly states 'Manifest of a stored build bundle by build_ref' and details what the manifest contains (files with sha256, byte length, text content status), which precisely identifies the resource and scope. It distinguishes itself from siblings by specifying it is metadata/discovery, not a file read, and explicitly names the sibling for reading a file.

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?

Explicitly provides usage context: 'Use tascan_get_build_file to read a file', and clarifies that 'Reading the manifest is discovery, not a read of any file'. It explains the protocol version and that build_ref is derived from tascan_get_task or tascan_get_cycle_report, giving clear when-to-use guidance and when-not-to.

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