Get Active Selection

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

Annotations provide readOnlyHint=true, so an agent already knows it's safe. The description then adds value by disclosing the returned data types (active object as primary, all selected objects, active tag/material) and the guarantee that handles are canonical and can be piped into other tools. It doesn't go deeper into rate limits or error cases, but it doesn't need to.

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?

Three sentences, all dense with information: what you get, why it's useful, and a note on output format. No filler, no restating of the tool name.

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 zero-parameter read-only query, the description is complete. It captures the return values and the primary use case (reacting to user's current focus). It could theoretically describe the data shape in more detail, but given the lack of output schema, the description does enough.

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?

The tool takes 0 parameters and the schema coverage is 100%, so there is no ambiguity. The description even mentions the underlying mechanism (canonical handles) that makes the output useful for chaining. Nothing is left undefined.

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?

Uses a specific verb+resource combination ('Read the active document's current selection') that clearly defines both action and scope. Names the primary entity, the full selection set, and two special cases (active tag, material), which distinguishes it from generic 'get' tools. The phrase 'without asking them to re-pick entities' positions it against interactive workflows.

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?

Delivers clear context: it is for reading the current selection and piping into describe/set_params/etc. This implies when it's the right tool (selection-reading) and names follow-on tools. The exclusion is inferable from context rather than explicit 'use X instead,' so it misses a full 5.

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