get_script_decisions

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

Annotations already say readOnly/idempotent/non-destructive, but the description adds substantial context beyond them: 'Reads only; nothing is sent to a provider', the extension 1.4.0 minimum, and the permission chain (agentAccess.scriptDecisions toggled by a person under Full access, Power User required, deviceEnabled/locallyPaused gating). That is exactly the operational context an agent needs to interpret empty or blocked results.

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 is front-loaded, but the body is one long parenthetical-heavy paragraph that packs provider values, state enumerations, and reason codes into run-on clauses. Given there is no output schema, most of that enumeration earns its place, yet it would read far better as short bulleted or semicolon-delimited segments.

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 carry the return shape, and it does: agent access flag, sign-in/plan requirement, device state, saved provider keys, per-script provider and state with all five state values and their reasons, plus the extra per-script data under scriptId. Nothing an agent needs to interpret this tool's output is missing.

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 already 100% for scriptId, so the baseline is 3. The description earns a 4 by explaining the semantic delta between the two modes: without the id you get every CM_decisions script, and with it you additionally get question-list hashes, code issues with line numbers, and today's decision rows — context the schema alone does not convey.

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?

Opens with a specific verb+resource: 'Read Script Decisions on this device', then pins the domain ('typed decisions scripts make through @grant CM_decisions'). It is clearly distinguishable from list_scripts (which enumerates scripts) and set_script_decisions (which writes), and it enumerates the exact facts returned, so an agent knows precisely what question this tool answers.

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?

Gives concrete ordering guidance: call before set_script_decisions because that tool names question lists by these hashes, and after export_script to check a provider. It also states the omit-scriptId listing mode. It stops short of naming when to prefer list_scripts or get_bridge_status instead, so it is strong but not fully exhaustive.

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