tvh_recording_action

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

Annotations already flag destructiveHint=true and readOnlyHint=false, but the description adds the crucial nuance that only remove_files destroys files while stop/cancel do not, plus an explicit consent precondition. It omits idempotency behavior (what a repeat 'stop' returns) and never mentions dry_run, which is the safety valve for a destructive mutation.

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 short clauses with no filler; the destructive warning is emphasized in caps and the consent rule follows directly. The mid-sentence line break between the stop/cancel clause and the remove_files clause slightly muddles front-loading of the most important information.

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?

An output schema exists and annotations cover the safety profile, so return values and risk framing need not be restated. But for a three-parameter destructive mutation with zero schema documentation, leaving dry_run and uuid unexplained leaves the agent without enough to call the tool safely in ambiguous 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 description coverage is 0%, so the description carries the whole burden; it does cover all three action enum values with real semantics, which is the most important parameter. However, 'uuid' is left entirely unexplained and 'dry_run' is never mentioned at all — a significant omission for a permanently-deleting operation.

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 defines each of the three action values with a specific verb and resource ('stop finishes an active recording', 'cancel cancels a timer/active recording', 'remove_files PERMANENTLY DELETES the recording files'), which lets an agent distinguish the enum cases. It never states the overall frame ('act on the recording identified by uuid') or differentiates itself from siblings like tvh_list_recordings or tvh_delete_node, so a 4 rather than a 5.

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 an explicit gating condition for the dangerous path: 'Use only when the user explicitly requests deletion of recordings', and the per-action definitions imply when to pick stop vs cancel. It offers no guidance on when-not to use the tool or which sibling to prefer for listing or rescheduling recordings, which keeps it below 5.

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