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

Beyond the annotations it discloses the actual match precedence (idempotency key, then open deal on title/company/contact), the exact contact-matching fallback rules, failure behavior on unknown fase, the default landing phase for new deals, the waarde-vs-productregels interaction, and a hint of the response shape ('aangemaakt: false'). This is consistent with destructiveHint=true (existing deals are overwritten via deal_id) and idempotentHint=true, and adds real mechanism rather than restating them.

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?

It is front-loaded with the upsert logic, which is correct, but the deeply nested parentheticals about contact matching ('hetzelfde bedrijf (of allebei zonder bedrijf) en hetzelfde contact. Zonder contact_id matcht alleen...') make for a dense, hard-to-parse single block. Every sentence carries content, but the structure could be split or bulleted for faster scanning.

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 17-parameter upsert tool with no output schema, the description covers the decision-critical behavior: matching, defaults, error modes, and idempotency. What is thin is what the call returns beyond the 'aangemaakt' flag and what happens to unspecified fields on an update, which an agent writing a retry or verification step might want.

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?

With 17 parameters at 59% schema coverage, the description carries meaningful extra load: it explains fase-is-a-name and its error mode, deal_id overwrite semantics, contact_id's effect on matching, and when to omit waarde. The remaining parameters (kans, type, agent, valuta, leadbron, omschrijving, verliesreden, eigenschappen) get no textual treatment, though their names and partial schema descriptions make them largely self-evident.

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 clause states a precise verb + resource combination ('Maak of werk een deal bij (upsert, geen dubbelen)') and immediately scopes it against a plain create by describing the de-duplication match rules. An agent can tell from the text alone that this is the write path for deals, distinct from the read-only siblings crm_deals and crm_pijplijn.

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?

It gives explicit when-to-use conditions for each mode: pass deal_id to update exactly that deal, omit it to upsert, omit waarde when productregels are supplied, and repeat idempotentie_sleutel on retries. What it lacks is routing guidance against sibling tools (e.g. use crm_deals or crm_zoek first to find an existing deal_id), so it stops short of full alternatives coverage.

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