get_convergence

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

With no annotations provided, the description carries the transparency burden. It does disclose a non-obvious behavioral trait: 'computes if not cached,' indicating possible computation and caching side effects. However, it omits other relevant details like whether the operation is read-only, potential error conditions, or whether computation is expensive. This adds some value but is not comprehensive.

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 a single concise sentence, front-loaded with the primary action and resource. It wastes no words and is appropriately minimal for a simple getter. The parenthetical adds necessary behavioral context without bloat.

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?

The tool is simple with one parameter and no output schema, but the description does not explain the return format, scale, or error behavior. It says 'convergence score' but not what the score represents or how to interpret it. The lack of annotations and output schema places a heavier burden on the description, which it only partially meets. This is adequate but with clear 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?

The schema has one required parameter, session_id, but the description does not explain its semantics, format, or how to obtain it. Schema description coverage is 0%, so the description should compensate, but it only references 'a session' without connecting to the actual parameter. The agent is left to infer that session_id is the session identifier, which is trivial given the name, but no further meaning is added.

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 function: 'Get convergence score for a session' with a specific verb and resource. It distinguishes itself from siblings like get_session (general session info) and analyze_convergence_trend (trend analysis) by focusing on the convergence score. The parenthetical adds a useful behavioral detail.

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 is provided on when to use this tool versus alternatives. While the description implies use for a single session's convergence score, it does not mention when not to use it, such as when needing a trend (analyze_convergence_trend) or loop detection (detect_loops). The absence of any exclusionary language leaves the agent without decision support.

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