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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds genuinely new operational context: per-call cost of $0.001 USDC via x402 on Solana and an equivalent HTTPS GET endpoint. That payment/auth detail is exactly the kind of behavior annotations cannot convey. It stops short of describing the response shape, but no output schema exists to lean on.

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 core semantics, then the parameter rules, then cost and alternate transport — a sensible order with no filler sentences. The pricing/HTTPS sentence is long and slightly disruptive to a math-focused description but is not waste.

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?

For a 4-param, 0%-schema-coverage tool with no output schema, the description covers the input side well but never says what comes back — seconds as a float? seconds plus frames? The agent can call it correctly but cannot anticipate the result value or unit, which matters for a duration conversion.

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 0%, so the description must carry all meaning, and it largely does: it defines the two input modes (code vs frames) and their mutual exclusivity, explains that a semicolon in the code selects drop-frame, and gives the exact per-frame duration for 24, 25 and non-drop 30 versus the NTSC 1001/30000 for drop-frame 30. The `drop` boolean is never explicitly tied to the frames-input path (only implicitly via the semicolon rule), which is the one real gap.

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 concrete computation: the exact wall-clock length of a frame count, with the per-frame timing rules that produce it. It is specific about the resource (timecode frames -> duration) but never names or contrasts with close siblings such as frames_timecode, timecode_frames, or duration_parse, so the agent must infer the boundary itself.

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 one real usage rule — 'Pass a timecode or a frame count, not both' — and explains that the semicolon form selects drop-frame. However there is no guidance on when to choose this over timecode_frames (frames from a code), frames_timecode, or timecode_add/diff, so selection among a crowded timecode family stays implicit.

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