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

Annotations cover read-only, idempotent, non-destructive and closed-world, so the bar is lower; the description still adds real context beyond them. It discloses that denominators, failed attempts and unverified annotations are surfaced in the result, and that no AI calls are made and no semantic text evaluation occurs — a meaningful scope constraint telling the agent mentions/recommendations must arrive pre-annotated.

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?

Four short sentences, front-loaded with what is computed, then the dimensions split, then result disclosures, then scope exclusions. No filler and no restatement of the title.

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?

No output schema exists, and the description partially compensates by naming the metrics and the denominator/failure/unverified reporting. However, for a tool taking up to 500 richly structured observation objects, it never explains the annotation contract — how mentioned/recommended booleans are validated, how citations are matched against owned_hosts, or what makes an annotation 'ungeprüft' — leaving an agent to guess at input correctness.

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 must compensate. It does so indirectly: 'annotierten Antwortprotokollen' maps to the observations array and 'eigene Quellen' (owned sources) maps to owned_hosts, giving both required parameters an inferable role. It adds nothing about the required per-observation fields (provider, surface, prompt_id, prompt, status), the enum semantics of status/location_access, or the verified/identity_verified flags.

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?

Names a specific verb ('Berechnet') and specific outputs (Nennungs-, Empfehlungs-, eigene Quellen- und Zitationsquoten) computed from a specific input class ('gelieferten annotierten Antwortprotokollen'). This separates it from siblings that fetch or produce data (analyze_web_performance, analyze_performance_export) by making clear it is a pure aggregation over already-supplied logs, though it never names the sibling it replaces.

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?

Usage is only implied: an agent infers 'use this when you already have annotated observations'. The negative constraints ('Führt keine KI-Anfragen durch', 'beurteilt keine Texte semantisch') rule out misuse, but there is no explicit when-to-use statement, no prerequisites, and no named alternative among the siblings.

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