amp_bookmark

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

No annotations exist, so the description carries the full load and does disclose the non-obvious behavior: omitting note auto-captures the transcript, and bookmarks are never auto-pruned (a durability guarantee). It does not state what is returned on success or how duplicate labels are handled, leaving a small gap for a mutation with zero annotation coverage.

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 identity and the resume-point framing, then requirements, then behavior, then triggers — a sensible order. It is dense but every clause carries information; only the phrasing is slightly em-dash heavy rather than wasteful.

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 two-parameter tool with no annotations and no output schema, the description covers purpose, required/optional inputs, the conditional behavior of note, durability, and when to call it. The remaining gap is return-value/error behavior, which is modest given the tool's simplicity.

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 50% (label is undocumented in schema), and the description compensates by labeling it "short name" and marking it required. The most valuable addition is the note-omission semantics, which materially changes what the call does and is not fully conveyed by the schema text alone.

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 — "drop a named session bookmark — a resume point" — and immediately clarifies the abstract concept with a concrete gloss. It also implicitly separates itself from amp_handoff by noting bookmarks surface in the next session's handoff, so an agent can distinguish it from the sibling tools without opening any schema.

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 concrete triggering conditions: user says "bookmark this" / "mark this point", before a risky change, or when the context window is filling up. That is clear positive guidance, but no explicit when-not or named-alternative routing (e.g. vs amp_handoff or amp_resume) is offered.

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