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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safe read-only nature is covered by structured fields. The description adds meaningful behavioral context beyond annotations: it certifies that no API key is needed (overcoming a common barrier), states that output is identical to a well-known URL (predictability), and instructs the agent to use the result for validation before acting (a behavioral guideline). It does not mention rate limits, but with zero parameters and read-only intent, this is acceptable.

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 two sentences and front-loads the most actionable info ('No API key needed — call this now'). The first sentence clearly states the purpose and the fields fetched. The second sentence adds a brief validation workflow. It is concise, but the emoji and urgent tone slightly reduce professionalism and the second sentence could be trimmed without losing meaning, so it loses a point for minor redundancy.

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 has zero parameters, simple read-only semantics fully covered by annotations, and an explicit output schema (not shown but noted as present), the description is complete. It covers what the tool returns (descriptor fields + runtime facts), how to use it (validation procedure), prerequisites (none), and how it relates to the sibling tool. An agent can invoke this correctly without additional information.

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?

The input schema is empty (0 parameters) and schema description coverage is 100%, so there is nothing for the description to add about parameter meaning. The description does add value by clarifying that no arguments are expected and that the owner is derived from the authenticated principal, which is explicitly stated in the schema's description. For a zero-parameter tool, the baseline for parameter semantics is high, and the description appropriately does not clutter with pseudo-parameters.

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 specifies a clear verb ('Fetch') and resource ('hash-verifiable AgentContractV1 descriptor' + 'hosted_runtime facts'), and explicitly distinguishes this from the sibling tool ('update_agent_contract') by noting it is a read-only retrieval identical to /.well-known/agent.json. It also names the exact fields returned (version, schema_url, schema_hash), leaving no ambiguity about what the tool does.

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?

The description explicitly states 'No API key needed — call this now,' telling the agent when to invoke it with no prerequisites. It also provides the validation workflow (fetch schema_url, match schema_hash), which is exactly the recommended usage. It distinguishes from the only sibling tool ('update_agent_contract'), providing implicit but clear contrast that this is for reading, not modifying.

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