start_print_recovery

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

Annotations already declare destructiveHint=true, readOnlyHint=false, and openWorldHint=false, so the safety profile is known without the description. The description adds that a session object is created which 'tracks the recovery lifecycle', but it does not disclose the real-world consequence of this action (physical printer motion, starting a job on a failed print) or how the session ends, which is the missing value-add for a destructive tool.

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 two-sentence preamble is front-loaded and clear, but the Args block duplicates the schema's parameter descriptions almost word for word, including the awkward wrapping, so a meaningful portion of the text does not earn its place. Structure is conventional but not optimized for an agent reader.

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 destructive, no-output-schema recovery tool, the definition covers inputs and the fact that a session is created but omits what the session returns (an id?) and what the agent should do next, such as polling get_recovery_session_status or calling complete_print_recovery. It is minimally adequate but leaves the post-invocation workflow undefined.

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 100%, so all four parameters are already documented in the schema, and the Args block merely restates those descriptions verbatim rather than adding meaning. The one genuinely useful detail is the 'same answer given to plan_failure_recovery' consistency constraint, but that phrasing is also present in the schema, so the description contributes little beyond it.

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?

The description opens with a specific verb and resource ('Begin executing a recovery plan') and adds that it 'Creates a recovery session that tracks the recovery lifecycle', which separates it from planning tools like plan_failure_recovery. It anchors itself to a sibling (plan_id comes 'from a plan_failure_recovery result'), so the agent knows this is a downstream step, though it never explicitly names the other recovery siblings it might be confused with.

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?

Usage is implied through the parameter notes: plan_id must come from plan_failure_recovery and part_attached/try_untested_resume must 'match' what was given there, which conveys prerequisite sequencing. However, it never states when NOT to call this (e.g., versus confirm_print_recovery, cancel_print_recovery, or complete_print_recovery) or what state the printer must be in, so the agent has to infer the workflow position.

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