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

Annotations only flag the write/destructive nature; the description adds genuinely non-obvious behavior: the write is stored but does not itself re-analyse, the prompt is caller-scoped and affects only that user's summary/key points/action items/notes, and the call needs recordings:write scope. Those facts are not derivable from the structured fields.

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?

Four short sentences, front-loaded with the action and identifier, then the differentiating scenario, then the effect scope, then the follow-up and auth requirement. No sentence is filler.

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?

Covers purpose, scoping, follow-up and required scope for a mutation tool with no output schema. It stops short of stating what happens when a custom prompt already exists (overwrite vs. error) despite destructiveHint=true, which is the one behavioral detail an agent would still want.

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 100%, so baseline is 3, and the description adds real meaning by explaining what customPrompt actually controls (the caller's own summary, key points, action items, enhanced notes) and that id is an integer UserCall id. It does not add anything about the account/workspace scoping parameters, which the schema already handles.

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?

States a specific verb and resource ("Set the custom prompt on an already-recorded call") with the identifier type. It also carves out the sibling boundary by naming the exact scenario (ad-hoc desktop/bot recordings without calendar events) that separates it from hub_set_event_custom_prompt and hub_set_series_custom_prompt.

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 use cases (meetings with no calendar event, re-analysing a call differently) and states the required follow-up step: "Stored only — follow it with hub_regenerate_summary to rebuild that version." An agent knows both when to reach for this and what to do next without inferring from sibling names.

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