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

Annotations already flag destructive/openWorld, but the description adds substantial context beyond them: it discloses that closing ends responses and posts to Ledger, that fielding spends credit for follow-ups/chats/analysis, that a live close is irreversible, and that it may return needs_confirmation. This is exactly the kind of behavioral disclosure that carries the burden annotations cannot.

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-loads the most important fact ('CLOSES the current wave') with no preamble, and every clause carries operational weight. It is dense with em-dash subordination but nothing is filler; slightly heavy for a single paragraph.

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 no output schema, the description appropriately surfaces the notable return (needs_confirmation) and covers destruction, credit cost, and irreversibility. The main gap is the absence of any guidance on the required seriesId and the approval/workspace parameters, which an agent must infer from the schema.

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 only 33% (only 'workspace' is documented; seriesId and approvalId are bare), and the description adds no parameter-level meaning for any of the three — no distinction between seriesId semantics, workspace selection, or how approvalId relates to the needs_confirmation flow. With low coverage, the description was needed to compensate and does not.

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 dual verb+resource (closes the current wave, fields the next one from the frozen instrument) and gives the scope ('a series'). This clearly distinguishes it from siblings like prism_series_create and prism_series_update, which manage series metadata rather than advancing waves.

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 an operational directive ('say both plainly before proposing') and notes manual launches don't move the schedule clock, which frames when to use it versus scheduler-driven launches. It does not explicitly name alternatives or state hard when-not conditions, so it stops short of a 5.

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