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

Annotations already declare readOnlyHint and idempotentHint, so the safety profile is covered; the description adds genuinely new context: there is no cost ('Free.') and the output deliberately omits the projection, which prevents an agent from calling it expecting a forecast. It does not describe freshness, caching, or failure behavior.

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?

Two short sentences, front-loaded with the cost signal and the scope, with the negative constraint placed last where it reads as a caveat. 'Free.' as a fragment is terse but earns its place as a routing signal; nothing is padded.

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?

There is no output schema, so the description carries the return-value burden, and it does so by naming the four provenance elements while explicitly excluding the projection. For a one-parameter read-only tool this is close to sufficient, though the response shape/format remains unspecified.

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 0%, but there is a single parameter whose allowed values are fully encoded as an enum (AMC/GME), making it self-documenting. The description only echoes those values ('for AMC or GME') and adds no meaning such as whether the symbol selects a data universe or a cached run.

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+resource ('Provenance preview of the current roadmap run') and enumerates the exact contents it returns: data providers, cross-check, reference archive, input hash. It also draws a scope boundary ('Does not include the projection'), but never names perpetual_status or perpetual_x402_contract to differentiate itself from them.

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?

'Free.' plus the exclusion of the projection implicitly signals this is the cheap, audit-oriented entry point, but there is no explicit statement of when to call this instead of perpetual_status or perpetual_x402_contract. The agent must infer the routing from cost and content hints.

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