forge

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

With no annotations provided, the description carries full burden and delivers comprehensive behavioral disclosure. It details the three action types (READ, MUTATION), file storage locations, runId validation with regex pattern, security guarantees against path traversal, authentication/network/rate limit status, and get behavior for unknown modules. It also explains version differences in state scoping and distinguishes safe vs side-effect operations.

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 description is well-structured with clear sections (purpose, behavior, usage guidelines, returns, example) and every sentence adds value. While comprehensive, it's appropriately sized for a complex tool with multiple operations. The front-loaded purpose statement immediately communicates core functionality, though some behavioral details could be more condensed.

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 complex tool with 4 parameters, no annotations, and no output schema, the description provides exceptional completeness. It covers purpose, behavior, usage scenarios, exclusions, security aspects, version differences, return formats for all three actions, and includes a concrete example. The description fully compensates for the lack of structured metadata, making the tool's functionality and constraints completely understandable.

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?

With 100% schema description coverage, the baseline is 3. The description adds meaningful context beyond the schema by explaining the runId's purpose in scoping state to forge runs and legacy behavior implications, clarifying that update action bumps counters and flags, and providing concrete examples of moduleId values. However, it doesn't elaborate on specific parameter interactions or edge cases beyond what the schema already documents.

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 explicitly states the tool's purpose as 'Read, update, or reset the per-module retry state for a forge run' with specific details about what it tracks (attempt count, score history, last status, last root cause, stagnation flag). It clearly distinguishes this from sibling tools by contrasting with session_state for cross-module reasoning and validate for recording validation attempts.

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 provides explicit 'Use when' scenarios with three concrete examples (orchestrator retry decisions, debugger inspection, resetting for fresh runs) and 'Do NOT use for' guidance that names specific alternative tools (session_state for cross-module reasoning, validate for recording attempts). This gives clear context for when to choose this tool versus alternatives.

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