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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context: 'nothing is persisted on this path' and 'A MODEL, not an observation' – clarifying that results are computed projections, not real-world data. This goes beyond what annotations provide.

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?

Three sentences with no fluff. The key facts are front-loaded: what it does, that it's a model, and that nothing is persisted. The 'A MODEL, not an observation' emphasis is a deliberate, useful clarification. Slightly more detail on parameters would be helpful, but the structure is efficient.

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 read-only, idempotent model run with no output schema, the description covers the essential behavioral contract. However, with 5 parameters and only 40% schema coverage, an agent may not know how to construct valid inputs (especially 'assumptions' and 'diversion_lag_hours'). The lack of output schema means return format is unknown, but the description's 'computed projection' gives some hint.

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 only 40%, and the description provides no parameter-level detail beyond what's in the schema. The description doesn't explain what 'assumptions' should contain, what 'diversion_lag_hours' means, or how 'closure_type' values map to scenarios. With 5 parameters and only 2 documented in the schema, the description should compensate but doesn't.

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: 'Run a chokepoint closure scenario' with a specific verb and resource. It also distinguishes itself from observations by noting it's 'A MODEL, not an observation.' However, it doesn't explicitly differentiate from the sibling 'run_sanctions_wargame' beyond the model name reference, so it's clear but not fully differentiated.

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 implies usage context by stating it's a model run and not persisted, but it doesn't explicitly state when to use this tool versus alternatives like run_sanctions_wargame or the query_* tools. The 'same model as the Chokepoint Simulator' reference provides some context but no explicit when/when-not guidance.

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