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

Annotations only declare readOnlyHint and openWorldHint, but the description adds substantial behavioral context: the six deterministic verdict states, the definition of the ±25% band, the exact rule that triggers too_uncertain (estimates >3x apart or non-positive), why `value` is null in that case, and how too_uncertain differs from no_value. It also discloses credits cost and anonymous rate limits.

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 definition is front-loaded and every part is substantive, but it is dense with stacked parentheticals and restates the band definition ('the callable band (the blend ±25%)' then 'The band is Deep Values' blended intrinsic value plus or minus 25%'). It is long for a one-ticker lookup, and some state machinery is repeated rather than compressed.

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, and the description compensates thoroughly by defining each returned field and the semantics of nulls and states — a lot to carry, done well. The remaining gap is input-side: the format/identity of `guru` and `ticker` is never resolved.

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 only 33% (only `quarter` is documented in the schema), so the description must carry the input burden. Instead it spends nearly all its text on output fields, leaving `guru` and `ticker` format unspecified (slug? numeric id? legal name?), which matters given sibling lookup tools such as guru and gurus.

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 first sentence names the specific resource ('one guru's disclosed move in one ticker') and enumerates the exact payload (legal name, three dates, quarter-end close, price, value band, verdict state), so an agent knows precisely what it will get. It never names a sibling (e.g. intrinsic_value, guru_moves) to draw the boundary, so it falls short of a 5.

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?

Usage is implied by 'one guru's disclosed move in one ticker' and enriched with practical constraints ('0.005 credits per call; works with no credentials up to 25 call(s)/day per address'), which is genuinely useful for deciding to call it. However, there is no when-to-use / when-not guidance and no routing to alternatives like intrinsic_value or guru_moves.

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