parseltongue_query

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

No annotations are provided, so the description carries the full burden. It fails to disclose whether this is a read-only evaluation, whether it can mutate state, what the query's side effects might be, whether the session must have a loaded DSL first, or what error behavior looks like for malformed WFFs. Returns are described only as 'JSON with query result' without structure.

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 docstring-style structure (Args/Returns) is familiar and compact, with zero wasted prose. However, the content is under-specified—merely parroting parameter names rather than enriching them—so while concise, it sacrifices substantive information for brevity.

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?

Despite an output schema existing (helps with return contract), this is a domain-specific query tool (parseltongue, WFF, sessions, DSL) with no in-description guidance about formula syntax, session requirements, or relationships to sibling tools. The description leaves the agent to discover critical context about what a WFF is and what querying entails.

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?

Input schema has 0% description coverage and both params (session_id, wff) have only type+title. The description merely restates the parameter names in the Args section without adding syntax, format, or semantics. Notably, the wider description (WFF, session) is in the Args/Returns, which is the only added value over schema. It fails to explain what a valid wff looks like or where session_id originates.

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 states it queries the system with a well-formed formula (WFF), giving a verb+resource that distinguishes it from session/document management siblings. However, 'query the system' is somewhat generic and doesn't clarify what kind of query (e.g., does it evaluate a CSL/DSL formula, a safety condition, a temporal query?). The term 'WFF' likely ties to parseltongue_check_consistency or dsl_reference siblings but the relationship isn't explicit.

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 provided on when to use this vs alternatives. It doesn't mention that session_id must come from parseltongue_create_session, or how this relates to check_consistency, load_dsl, or the dsl_reference tools. The agent has to infer context from sibling names.

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