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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so safety is covered. The description adds distinct context not in the annotations — no auth or signer required ('keyless, nothing to sign') and the data provenance (computed live from the venue's own per-gauge figures). It does not describe output shape, but an output schema exists.

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 'call before' instruction is well front-loaded, but the description repeats itself: 'Free, keyless, read-only' is restated verbatim in the closing 'Cost and signer: free and keyless, nothing to sign.' The middle sentence is a dense run-on mixing the measured figure with a causal claim, which dilutes scannability.

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?

Output schema and annotations carry the return-value and safety burden, and the description covers when to call it and where the numbers come from. The gap is scope: with zero parameters the description still says it measures 'the fraction of system votes a position actually holds' without explaining what position or whose, leaving the agent unsure what the tool is reporting on.

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 tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline for a 0-param tool is 4. The description correctly says nothing about inputs, though it could clarify whether the 'position' it reports on is scoped somehow given no parameters exist.

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 states a concrete comparison: the venue's advertised weekly number beside the money actually collected, computed live from per-gauge data (fees and bribes distributed vs. vote share held). That is a specific verb+resource an agent can act on. It stops short of naming a sibling tool, though the prefix and framing distinguish it reasonably from hydrex_position / hydrex_vault / hydrex_votes.

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?

Timing is explicit and front-loaded: 'Call this before repeating any Hydrex APR or yield projection,' which tells the agent exactly when this must be invoked. There is no exclusion clause naming an alternative tool for the opposite case, so it lands at 4 rather than 5.

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