loop_record_attempt

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

The description goes beyond the annotations: annotations only declare readOnlyHint=false and idempotentHint=false, while the text adds that this mutates persisted state and that the loop 'auto-exhausts after max failed attempts' — a consequential lifecycle behavior an agent must know before calling. It does not cover what happens to previously recorded attempts or error behavior when the loop is inactive.

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?

Two short sentences with no filler, and the core action is front-loaded before the side effect. Slightly terse on terminology ('loop contract' is unexplained), but nothing is redundant.

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 6-parameter state-mutating tool with no output schema, the description covers the key behavioral consequence but omits the prerequisite state (loop must be active), what the append does to the attempt counter that triggers exhaustion, and the cwd/workspace_root context that the schema leaves lightly described. Adequate but with meaningful gaps.

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 83%, so the schema already documents id, verdict, evidence, authority_file, and workspace_root, including the pass/fail verdict values. The description only echoes 'pass/fail' and 'evidence' from the schema and adds no new meaning, so the baseline 3 applies.

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 names a specific verb and resource — 'Append a pass/fail attempt with evidence to an active loop contract' — which clearly separates it from loop_start, loop_stop, and loop_status. It stops short of explicitly naming a sibling or alternative, so it lands just under a 5.

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 'active loop contract' implies a prerequisite (a loop must already be running, presumably via loop_start), but this is inference rather than an explicit when/when-not rule. No guidance is given on when to prefer this over loop_status for checking progress, so usage is only implied.

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