replay_start

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

Annotations already declare write, non-idempotent, open-world, non-destructive behavior, so the safety profile is largely covered. The description does add one genuine behavioral fact beyond that: the operation verifies the cursor and aborts on excessive unapproved relocation, which explains the expected_layout_id and maximum_relocation_seconds guards. It still omits what state is changed in the terminal, whether a prior session must be stopped first, and how failures surface.

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?

A single front-loaded sentence with no filler, leading with the verb and resource before the safety clause. It is compressed close to the point of terseness ('verify cursor' is vague about who verifies what), but nothing is wasted.

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 non-idempotent, state-changing replay control with no output schema and three required parameters, the description covers the layout guard and relocation abort but says nothing about the resulting replay state, prerequisites, or how the caller learns the start succeeded. Adequate but with clear gaps.

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 only 40%, and the description compensates partially by clarifying that 'time' is Unix seconds and that relocation must be approved via the relocation parameters. However allow_relocation and maximum_relocation_seconds are never explained in prose, and their interaction with the 'unapproved relocation' stop rule is left ambiguous.

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 ('Start browser Bar Replay') plus the timestamp format ('Unix-second'), which is more than the name alone conveys. It does not explicitly set itself apart from siblings such as replay_step or replay_autoplay, so it stops short of 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?

There is no statement of when to use this versus replay_step, replay_resume-style autoplay, or replay_stop, and no prerequisites (connected terminal, chart ready) are given. The only guidance is a post-start safety check, which is not usage routing.

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