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

Annotations already declare readOnly/idempotent/non-destructive; the description goes well beyond them by disclosing the keyword fallback when no embedding model is configured (with the literal 'mode':'keyword' marker), the possibility of an empty list rather than a forced match, ranking by semantic similarity, lightweight-row responses, and the 'connected' flag semantics.

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 purpose, then behavior, then the workflow chain — every sentence carries information and none is filler. Sentences are dense and long, which slightly hurts scanability.

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 compensates by describing the return shape (ranked lightweight rows, connected flag, mode field) and the empty-result case, and it maps the tool into the broader action-execution workflow. Nothing an agent needs to select or invoke it correctly is missing.

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 100%, so the baseline is 3; the description nonetheless adds operational meaning to pieceName ('optionally scope to a single piece') by tying it to the catalog-wide default. limit's max/default are left to the schema, but nothing is genuinely missing.

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?

Specific verb+resource: 'Find piece actions by natural-language task description', with a concrete example. It is clearly distinguishable from siblings like ap_search_triggers (triggers, not actions) and ap_research_pieces.

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?

Explicitly frames itself as 'the discovery step' and names the exact follow-on chain (pieceName + actionName -> ap_get_piece_props -> ap_run_action). It also states the no-match behavior. It does not, however, contrast against the adjacent sibling ap_search_triggers, so an agent must infer when to prefer one search over the other.

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