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

Annotations only mark readOnlyHint=false, but the description adds valuable behavioral context: 'Max 2 MiB', 'sealed=true ... never served back', 'Returns sha256 and afg-cas:// uri', and the crucial 'TEST MONEY ONLY: mock ledger, test tokens (tUSDC), no real funds'. No contradiction with 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?

Three sentences, front-loaded with the action and endpoint, followed by use case, constraints, return value, and test environment. Every sentence earns its place with zero filler.

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?

Covers endpoint, intended use, size limit, return format, and test-only nature. The schema covers parameter details and the signing flow. Minor gap: no guidance on precedence or exclusivity of content_b64 vs content_text when both are supplied.

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. The description adds meaning beyond the schema by stating the 'Max 2 MiB' size limit and explicitly instructing to 'set sealed=true for hidden tests', which reinforces the schema's 'Hidden input, never served' note.

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: 'Upload bytes to AFG's content-addressed store' with explicit endpoint 'POST /v1/artifacts'. The opening sentence unambiguously distinguishes this from sibling operations like afg_submit or afg_sign_contract.

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 concrete use context: 'Use for pinned contract inputs (repo tarball, schema)' and clarifies sealed=true for hidden tests. Does not explicitly name excluded alternatives, but the intended scope is clear.

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