query-session

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 describes the core behavior (attempting to prove a goal from accumulated premises) and includes an example showing expected inputs/outputs. However, it doesn't disclose important behavioral traits like error conditions, performance characteristics, what happens when the goal cannot be proven, or whether this is a read-only vs. mutating operation. The example adds some context but leaves gaps.

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 perfectly structured and concise. It leads with the core purpose, follows with usage guidelines, and provides a concrete example. Every sentence earns its place: the first states what the tool does, the second tells when to use it, and the example illustrates practical application. No wasted words or redundant information.

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 the complexity (a query/proving tool with 4 parameters), lack of annotations, and no output schema, the description is moderately complete. It covers the purpose and usage context well but doesn't fully address behavioral aspects like what the response contains, error handling, or performance considerations. The example helps but doesn't substitute for explicit behavioral disclosure. For a tool of this complexity, more complete behavioral information would be beneficial.

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 the schema already fully documents all four parameters. The description doesn't add any parameter-specific information beyond what's in the schema descriptions. The example shows usage of 'session_id' and 'goal' but doesn't explain their semantics further. With complete schema coverage, the baseline score of 3 is appropriate.

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 the tool's purpose: 'Query the accumulated knowledge base in a session.' This specifies the verb ('query') and resource ('accumulated knowledge base'), and distinguishes it from siblings like 'list-premises' (which lists premises) or 'prove' (which might be a different proving mechanism). However, it doesn't explicitly differentiate from 'find-model' or 'find-counterexample' which are also query-like operations.

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 usage guidance: 'After asserting premises, query for a conclusion.' This clearly states when to use the tool (after premises are asserted) and implies an alternative workflow (premises must be established first). It doesn't specify when NOT to use it or name alternatives directly, but the context is sufficiently clear for effective tool selection.

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