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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower; the description still adds real value with the paid-account auth requirement and the precise scope (only explicitly saved research notes, not files or conversations). It stops short of describing pagination or result format.

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?

One compact sentence carrying scope, exclusions and prerequisite, with the core action front-loaded. No padding, though the language mismatch with the English tool name slightly hurts scannability.

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 simple read-only tool with no output schema, the description covers scope and auth but omits the meaning of the offset parameter and any sense of return volume or pagination, which are the main open questions an agent would have.

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 0%, so both parameters (dossier_id, offset) are undocumented. The description only vaguely implies dossier scoping via 'je eigen dossier' and says nothing about what offset paginates or how it behaves, leaving the agent to guess.

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+resource combination ('leest ... bewaarde onderzoeksnotities in je eigen dossier') and scopes it against non-dossier content ('geen bestanden of overige gesprekken'), which helps separate it from siblings like fetch and search. It is clear what is read, though it doesn't name a sibling tool directly.

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 gives implicit when-not guidance by excluding files and other conversations, and states a prerequisite ('Betaald account nodig'). However it never names an alternative tool (e.g. list_saved, search) or the condition that should route the agent there, so usage is only implied.

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