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

Annotations indicate a non-read-only, non-destructive mutation, and the description adds the meaningful detail that the marker is stamped at the current time rather than an arbitrary one. It does not disclose whether markers are persisted, whether captions are editable or required to be unique, or what happens on failure; with no output schema, that return/failure behavior is left implicit.

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 or repetition. It is efficient, though the extreme brevity is a completeness trade-off rather than a model of density.

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 one-parameter mutation tool with no output schema and no parameter documentation, the description should at minimum explain what caption means and what the agent sees back. Neither is covered, leaving the only input field unexplained.

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?

There is exactly one required parameter, 'caption', with 0% schema description coverage, and the description never mentions it. The word 'chapter' only faintly hints that caption is the chapter label; a reader cannot tell whether it is a title, a note, or free-form text.

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+resource: adds a chapter marker at the current time of the running recording. This is enough to distinguish it from record_start and record_stop siblings, though the wording 'chapter' versus the tool name 'record_marker' is a slight terminology mismatch.

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?

The phrase 'of the running recording' implies the prerequisite that a recording must already be active, which is useful context. However, it never states what happens if no recording is running, nor does it explicitly direct the agent to record_start first.

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