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

Annotations only declare readOnlyHint=true; the description adds real behavioral context beyond that: 'costs nothing, writes nothing — one read', the counting rule that unreviewed clips count as takes_clip but never as gewaehlt, and that an unproven shot in the sequence is excluded from coverage and surfaced separately. These are non-obvious semantics an agent cannot infer from the annotations.

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?

Purpose and scope are front-loaded, and the field-by-field enumeration is justified because there is no output schema to carry it. The density of German field names makes it heavy, but each sentence contributes either a return shape or a counting rule, so little is wasted.

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, this description carries the full burden and does so: it documents every returned section (takes_bild/takes_clip, gewaehlt, referenzen, im_schnitt, luecken, kopf) plus the aggregation fields. Given a single trivial parameter and read-only behavior, an agent has everything needed to call and interpret it.

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 coverage is 100% and the single project_id parameter is fully documented (including the lab_list_projects provenance), so the description need not repeat it. The description still adds meaning about what values the id can designate, e.g. a project with no shotlist is a valid input returning kopf.hinweis='keine_shotliste'.

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 ('Read how far each shotlist shot ... is covered') and enumerates the concrete dimensions of coverage (takes, chosen take, bindings, cut). It also explicitly distinguishes itself from the nearest sibling, lab_shots, so an agent can separate the two without opening either schema.

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 closing sentence names the alternative tool and the exact condition that selects between them: lab_shots reads the shot layer of a sequence, this one reads project-level shotlist shots and their material. It also clarifies the legitimate empty-case (no shotlist = a finding, not an error), which prevents misuse as an error path.

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