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

With no annotations, the description carries the full burden and does disclose a genuinely non-obvious side effect: saving automatically updates the reference graph. It also clarifies the semantic effect of isNextAction (sets the next event date). It does not mention permissions, failure behavior for invalid chip IDs, or what the call returns, which keeps it short of a 5.

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?

Purpose is front-loaded in one clause, followed by flag behavior, then the chip pattern with a parenthetical list of supported types, ending with a concrete example. Every sentence adds information; the final example is slightly redundant with the preceding sentence but earns its place by making the syntax unambiguous.

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 5-parameter mutation tool with no annotations and no output schema, the description covers the core write behavior, the next-action flag, and the linking mechanism well. It leaves isArchived unexplained and says nothing about the response or about what happens when a chip references a missing entity, which matters for a write operation with graph side effects.

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 only 40%, so the description must compensate, and it does for the two most ambiguous parameters: isNextAction is fully explained and the description field's chip syntax is specified with a concrete worked example ($[note:42:Contrato]). expedientId and isArchived remain unaddressed in both schema and description, so one parameter is still opaque.

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 opening sentence gives a specific verb and resource in domain terms ('Añade una línea de actuación a un expediente'), so an agent knows immediately this creates an entry inside an expedient. It does not name or contrast with any sibling (e.g. expedient_lines_list or expedients_update), so differentiation is inferred from the verb rather than stated.

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?

The description explains how to use the isNextAction flag and how to embed resource chips, which is practical invocation guidance. However, it never says when to use this tool versus alternatives, gives no preconditions (must the expedient exist?), and offers no exclusions or when-not guidance.

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