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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, yet the description adds genuinely new behavior: the tool fetches the structured meeting and agenda itself so the host only supplies meeting_ids, unknown ids / agenda-less meetings / out-of-horizon meetings produce an explicit validation error rather than a plausible empty note, and email delivery plus the Friday/Monday cron are separate infrastructure. That is exactly the extra context the annotations cannot carry.

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?

Bold headers and short paragraphs make it scannable, but the opening 'Bij commissievoorbereiding' workflow paragraph substantially duplicates the later 'Positie in de keten' section, and the actual purpose statement is pushed to the second block. Roughly a quarter of the text is restated workflow rather than tool-specific information.

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 return-format burden and does so ('Retourneert: markdown — bolletjes-legenda + agenda-overzicht + per-vergadering detailblok op maat'), and it covers the failure mode for bad ids. Only vandaag and the 25-item meeting_ids cap are left unexplained.

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 the description has to carry the load and largely does: it says to take naam/partij from mijn_fractie_context, fill covered_topics and followed_committees with confirmed values or empty lists ('verzin ze niet'), and supply meeting_ids from lijst_vergaderingen. The ~2-week framing maps to horizon_dagen and vandaag is only implied by the workflow, so one parameter is left to inference.

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 description states a concrete verb and artifact: 'Stelt de fractienotitie samen' — an agenda overview for the coming ~2 weeks on the user's portfolio, with a 🟢/🟠/🟡/⚪ legend and per-agenda-item detail blocks whose depth is user-relative. That is far more specific than a restated name. It does not, however, differentiate itself from the listed siblings (genereer_raadsstuk, adviseer_raadsinstrument), so an agent must infer the boundary.

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?

'Gebruik wanneer: de gebruiker een fractienotitie/voorbereiding voor de komende vergaderingen wil' gives an explicit trigger, and the chain section spells out prerequisites (call mijn_fractie_context first, then lijst_vergaderingen with sortering='oudste_eerst', pass the ids as meeting_ids). There is no when-not guidance or named alternative among the siblings, so it stops short of a 5.

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