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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, and the description reinforces rather than contradicts them with concrete scope: "Read-only English lexical matching; no installation, execution or sharing." It also discloses the default response shape (one candidate, source pins, environment, evidence/recall summaries, setup argv) and the contract_url prerequisite — context annotations cannot express.

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?

The purpose is front-loaded and length is proportionate for a 13-param tool, but the middle sags into tangled fragments: "Use detail=execute for the complete execution contract in this same lightweight response; otherwise read selected.contract_url before execution" requires re-reading, and "detail=full restores the legacy combined view" is changelog residue rather than actionable guidance.

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 partially compensates by enumerating the compact payload and pointing at selected.contract_url. But for a tool with 13 undocumented parameters and two enums, it leaves critical unknowns: what query_mode changes about matching, what the free-text filter params accept, and what the limit maximum of 3 implies for retrieval strategy.

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 description coverage is 0% across 13 parameters, so the description must carry the load — but it explains only `detail` (compact/execute/full). The 10+ filter parameters (os, robot, python, runtime, controller, hub_commit, observation, architecture, runtime_version, limit) and the semantically important query_mode enum are entirely undocumented; "Supply only known filters" is cryptic rather than clarifying.

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 outcome: "Find an executable starting point for a robot task," which usefully corrects the potentially misleading name (it does not start anything). It does not, however, differentiate itself from siblings like find_robot_skills or inspect_robot_skill, so an agent must infer the boundary.

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 description gives real workflow guidance around the detail modes ("Use detail=execute for the complete execution contract... otherwise read selected.contract_url before execution" and "Read applicable recall details before reuse"). But it never says when to pick this tool over find_robot_skills or inspect_robot_skill, nor when to use query_mode=task vs all_terms, leaving the primary selection decision implicit.

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