Set a control's text (experimental)

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

Annotations already declare destructiveHint=true, readOnlyHint=false, idempotentHint=false and openWorldHint=true, but the description adds genuinely non-obvious behavior: the write bypasses the keyboard, it can silently no-op on many web editors, and the caller must verify the reported value. It also classifies the tool as 'controlling the computer', which calibrates agent caution. It stops short of warning that existing text is irrecoverably overwritten, which is the main destructive risk left implicit.

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?

Front-loaded with the experimental mechanism and the mechanism contrast, then the usage caveat, then the safety classification. Almost every sentence earns its place, though the phrase 'found with nvda_find_objects and window' is slightly compressed to the point of ambiguity, and the closing line partially repeats the sibling framing already implied.

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 annotations covering the safety profile, an output schema covering the return value, and 100% schema coverage on 7 params, the description only needs to supply the failure model and fallback — which it does. The remaining gap is minor: the record/record_within recording behavior, which can make NVDA silent for seconds, is explained only in the schema, not flagged in the description.

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 id, text, record, settle_ms, timeout_ms, until_speech and record_within are all documented in the schema itself. The description adds only indirect meaning for 'id' (that it comes from nvda_find_objects and can be a window) and nothing about record/settle/timeout tuning. Baseline 3 is appropriate when the schema carries the semantics.

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 and resource ('give an edit field new text through its accessibility API') and immediately distinguishes the mechanism from the sibling tool ('instead of the keyboard'), naming UI Automation ValuePattern / IAccessible accValue. It also states the post-condition ('report the value it has now'), so an agent knows both the action and the feedback loop without opening the 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?

Explicit when-to-use is given ('It needs no focus, so it can reach a field in a background window, found with nvda_find_objects and window'), plus an explicit when-it-fails condition (React/Lexical/WhatsApp Web editors) and a named fallback path ('use nvda_focus_object and nvda_type_text'). This is the full when/when-not/alternative triad.

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