Cesium Map

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

Beyond the annotations, the description discloses real operational behavior: it creates a live browser session that takes time to connect, it returns a sessionId that must be threaded through every map tool, and repeated calls are for reopening known sessions rather than duplicating. It omits what happens on timeout/failure or how long to wait before commands, which is the remaining gap. Note the mild tension between the session-creating behavior and readOnlyHint, though no data is mutated.

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?

Four short sentences, front-loaded with what the tool does and followed by the sessionId contract and the connect-wait rule; no filler or restated title.

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 one-optional-parameter, no-output tool, the description covers the essentials an agent needs: it returns a sessionId, must be called once, and requires waiting for connection before issuing commands. Error/timeout behavior and whether a second open call replaces or duplicates a session are the only meaningful omissions.

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 0% and the only parameter is undocumented in the schema, so the description has to carry it. "Optionally reopen a known session" plus "Pass the returned sessionId to every map tool" does establish that sessionId is optional and identifies an existing session, which is meaningful added semantics, but it never states the format or what an invalid/expired id yields.

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?

"Open an interactive 3D map beside the conversation" is a specific verb plus resource, and the note about passing the returned sessionId makes the tool's role as the entry point of the map workflow clear. It stops short of naming sibling tools (connectCesiumMap, exchangeCesiumMap) as alternatives, so differentiation must partly be inferred from the lifecycle sentence.

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?

"Call once to open the map, then wait until its browser session connects before sending commands" gives explicit sequencing and a precondition, and "Optionally reopen a known session" covers the second call pattern. It never says when NOT to call it or which sibling to use instead (e.g. connect vs exchange), leaving the alternative path implicit.

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