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

Goes well beyond the annotations: declares determinism, no network access, no stored state, and concrete operational limits (64 KB input, 1 s per call, 1 MB result). These are consistent with readOnlyHint/idempotentHint/destructiveHint=false and add usable context an agent cannot get from structured fields alone.

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?

Front-loads the action, then the decision outputs, then when/when-not, side effects and limits — a good order. The ES and EN versions are full duplicates, which doubles the length for no additional information, though the redundancy is deliberate for language coverage.

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?

For a stateless ranking computation with an output schema (so return values need no prose) and a well-covered schema, the description supplies everything else an agent needs: trigger condition, exclusion, safety profile, determinism and hard limits.

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?

With 100% schema description coverage, the schema already documents id, flags, sources, build_days, check_days, feasibility, value_units, read_allowed and total_sources. The description only alludes to 'conteos de evidencia, factibilidad y esfuerzo' without adding syntax or defaults, so baseline 3 is appropriate.

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 concrete verb and resource — ranking up to 8 candidate opportunities — and enumerates the exact output decision classes (BUILD_CANDIDATE_MODELLED, INVESTIGATE, DISCARD, ABSTAIN, DENY) plus the scoring basis. Also explicitly distinguishes itself from the nearest sibling, stats-forecast.

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?

'Cuándo' gives the triggering situation (an agent has candidate needs/ideas with rough evidence counts and effort and must pick which to build, check or drop), and 'No para' names the alternative (stats-forecast) with the condition that selects it. Nothing is left to inference.

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