Read a group's or the selection's grid

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

With no annotations supplied, the description carries the full burden and does so: it declares read-only up front, states that reading a group does not select anything, discloses ordering semantics (patch order vs selection order), notes MAtricks transformation is applied to the live selection, warns that 'Distributions follow the cells, not the list order', and lists the returned fields including PreserveGridPositions, lock, shared cells, bounds and gap count. It also flags the bridge 0.21.0 prerequisite.

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?

The read-only flag and the group/no-group split are front-loaded, and most sentences carry distinct facts. It is, however, a single dense run-on block with listed return fields that could be trimmed or laid out more scannably, which keeps it below 5.

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 two-parameter read tool with no annotations and no output schema, the description covers everything an agent needs: mode selection, ordering, MAtricks interaction, what the numeric cells mean versus stage positions, the shape of ids, and a version prerequisite. Nothing material is left to inference.

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 100%, so the schema already documents both 'group' and 'data_pool' fully, making 3 the baseline. The description reinforces what omitting 'group' means and clarifies the ID format of returned fixtures (FIDs or dotted cell ids like "501.1"), but adds nothing about the 'data_pool' parameter that the schema does not already carry.

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 names a concrete verb and resource and splits it into two clearly enumerated modes: 'With group: the stored fixtures of Group <n> ... with their selection-grid X/Y/Z cells' versus 'Without group: the current selection in the order it was selected'. It also pre-empts confusion with the similarly named sibling gma3_fixture_positions by stating 'Grid cells are the selection grid MAtricks and phasers use, not physical stage positions.'

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 selection logic for the two modes (pass group to read stored data with nothing selected; omit it to read the live selection), which is stronger than most siblings. It stops short of naming alternative tools for physically-oriented queries (e.g. gma3_fixture_positions or gma3_matricks) as the destination when this tool is wrong.

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