Observe current game state

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

With no annotations, the description carries the full burden and largely succeeds: it discloses the return type (formatted text, or a JSON string via format), the 40-item pagination window, the exact truncation header format ('Inputs (41-80 of 132)'), and the token-saving behavior of since_last. It stops short of stating rate limits or the full shape of the observation, but the read-only nature is clear.

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?

Front-loads the read purpose, then return format, then pagination mechanics, then alternatives. Dense and each sentence is informative, though the pagination example adds some length; overall efficient with no filler.

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 an 8-parameter read tool with no output schema, the description explains the return values (text vs. JSON string) and the pagination behavior an agent must act on. It is complete enough to call correctly, though it could say slightly more about the JSON variant's structure.

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 coverage is 100%, so the baseline is 3 and the schema already documents every parameter. The description adds cross-parameter workflow meaning: how inputs_offset pairs with the truncation header, that since_last is ignored in json format, and the token trade-off of polling versus fetching variables.

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?

States a specific verb and resource ('Read the current passage') and enumerates exactly what is read: text, numbered choices, input fields, dialog state, status text. It distinguishes itself from find_ui ('jump to a specific control') but does not differentiate from closer siblings like inspect_ui or live_view, leaving some ambiguity.

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?

Explicitly routes to alternatives with conditions: find_ui(text) for a specific control, get_variables for specific story variables, and since_last=true when polling to save tokens. Both when-to-use and sibling selection are covered without inference.

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