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

Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=true), so the bar is lower. The description adds a useful behavioral contract the annotations cannot convey: the response may include next_offset, which must be fed back as offset for the next page.

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?

Three short sentences with zero filler; the core read is front-loaded, the enum gloss follows, and the pagination tip is last where an agent will look after a first call.

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 no output schema, the description carries the burden of return-value behavior, and it does disclose the key pagination field. It stops short of describing the shape of an idea object or an empty-result case, which would complete the picture for a 3-parameter listing tool.

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 does add value by glossing the category enum ('user' = human ideas, 'bisociation' = bisociations) and showing how offset is driven by next_offset, but limit and offset semantics remain fully schema-defined.

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 specific verb and resource in Spanish ('Lee las ideas y bisociaciones del Banco de Ideas'), so the agent knows this is a read over the idea bank. It does not explicitly distinguish itself from the sibling buscar_ideas, so it stops 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?

Gives the filter options ('user', 'bisociation', 'all') and the pagination recipe (pass next_offset as offset), which is real usage context. However, it never says when to prefer this over buscar_ideas or how it relates to leer_idea, so guidance is implied rather than explicit.

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