parseltongue_check_consistency

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. The description explains the tool 'verifies' claims and returns a report, but doesn't state whether this is read-only, whether it modifies session state, what side effects occur, performance characteristics, or how the verification works. For a diagnostic/analysis tool with zero annotation coverage, more behavioral context is warranted.

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 compact and well-structured with Args/Returns sections. It earns its space with the three-category result explanation (verified, unverified, inconsistencies). Minor waste: returning 'JSON with consistency check results' is partly redundant given that an output schema exists, but overall it's efficient and readable.

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?

Given an output schema is present, return format doesn't need elaboration. The tool is moderately complex (a multi-faceted consistency analysis). However, the description covers the core behavioral scope and parameter. Gaps: no mention of failure modes, edge cases for empty sessions, or how results relate to registered documents/DSL. Adequate but not fully complete for a diagnostic tool.

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%, and the description only restates the parameter name ('session_id: Session ID') without adding semantic detail — no explanation of what a valid session ID looks like, where to obtain one, or what happens with an invalid/absent session. The description does not compensate for the zero schema coverage, so the single parameter remains underdocumented in meaning.

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 clearly states 'Run full consistency check on the session' — a specific verb+resource combination. It explains what the check verifies (claimed vs unverified claims vs logical inconsistencies). It doesn't explicitly distinguish from sibling tools like parseltongue_get_state or parseltongue_query, though the scope ('full consistency check') is reasonably distinct.

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?

No guidance on when to use this tool versus alternatives. There's no statement of prerequisites (e.g., whether a session must exist first, whether documents must be registered before the check), no when-not-to-use guidance, and no mention of expected preconditions. The description implies usage (on a session) but doesn't explain context like when consistency checking is appropriate.

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