describe_configuration

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

With no annotations, the description carries the full burden and does reasonably well: it discloses that values collapse to a single number when all instances are equal and otherwise report min/max/count, and that certain attributes appear only conditionally. It never explicitly says the operation is read-only or side-effect free, but the detail about returned content is above the annotation-free baseline.

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 description is dense but front-loads the core purpose (what gets described) before the parameter guidance, and most sentences carry real information. The conditional-attributes sentence is somewhat confusing and could be trimmed, but there is little outright waste.

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?

There is no output schema, so the description must explain the return shape, which it does thoroughly for a complex config-inspection tool. Gaps remain around the group/model parameters and the read-only nature, but an agent has enough to call it correctly for most cases.

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 0%, so the description must compensate, and it largely does: config is explained as the file name with or without '.lsd', object selects a single object, and detail='names' alters output granularity. group and model are left unexplained, and the 'Set only when they apply: computed=false ... debug, plot, parallel, saved_separately' sentence ambiguously mixes output attributes with settable fields.

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 specific verb ('Describe') and resource ('.lsd configuration') and enumerates exactly what is returned: the object tree with instance counts, per-element type/lags/saved flag/value summaries, and run settings. This is clearly distinguishable from siblings like read_equations, read_results, or list_models.

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 practical guidance for large models ('pass object=Name ... or detail=names'), which is useful invocation context, but never states when to prefer this tool over alternatives such as read_equations or read_results, nor any exclusions. Usage is implied through parameter selection rather than explicit routing.

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