Relacionar, analizar vínculo o correlacionar identidades

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

Annotations already cover the write/idempotent/safe profile, and the description adds genuinely new behavior: the 0.85 auto-link threshold for correlate (an automated mutation the agent would otherwise not expect) and the fact that correlate with an empty target compares against the whole case. Minor tension worth noting: unlink 'elimina la relación' while destructiveHint=false — the edge deletion is at least disclosed, so it is not a contradiction, but the reversal story (is the deleted edge recoverable?) is never stated.

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?

A single semicolon-delimited sentence organized by action, front-loading the default mode first. Dense but zero waste — every clause carries a distinct behavioral fact.

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?

With 12 parameters and no output schema, the description never indicates what analyze or correlate return (an inferred role/sentiment/weight? a probability score? whether a link was created at the threshold). For a multi-mode tool this leaves the agent guessing at results and at entity-existence prerequisites.

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 100%, so the baseline is 3; the description earns above that by mapping the optional HUMINT trio (rol, sentimiento, peso) to the link/analyze actions, which the schema only documents in isolation. It does not explain how source, edge_label, confidence or properties interact with each action.

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?

Enumerates all four modes with concrete semantics: link crea/refuerza la relación dirigida source->target, analyze infiere rol/sentimiento/peso, correlate calcula probabilidad de solapamiento y enlaza si >=0.85, unlink elimina la relación. An agent can pick the right mode without opening the schema, and no sibling (osint_upsert_entity, osint_get_neighbors, osint_find_paths) does the same job.

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?

Each action's effect is described, which implies when to use it, but there is no explicit guidance on choosing between analyze and correlate, nor any stated prerequisites (entities must already exist, likely via osint_upsert_entity). No exclusions or pointers to sibling tools are given.

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