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

Annotations already declare it as a non-destructive read, so the safety profile is covered; the description adds genuinely new context by disclosing the delta semantics ("what the human did since your last read"), which explains why idempotentHint is false. It could still say more about what happens on concurrent reads, but the added behavioral value is real.

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?

Dense but front-loaded: the live-session restriction and read purpose come first, then the return contents, then the wait workflow. Nearly every clause carries information, though the final workflow sentence is slightly packed.

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?

With no output schema, the description carries the burden of describing returns and does so concretely (player state, plays, errors, silences, taps, remember() changes, code, Pass, End). An agent has everything needed to call it correctly and interpret the result.

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 baseline is 3; the description earns an extra point by explaining the practical effect of wait:'pass' (a whole back-and-forth set in one turn) beyond the schema's mechanical timeout description. The session id parameter is well covered by the schema pattern.

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 (reads) and resource (live session state) and enumerates exactly what is returned: whether the player is up, what it played, errors, silences, and human actions. It distinguishes itself from siblings by tying session creation to play-live-pattern and the write path to update-session.

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?

Gives an explicit precondition ("Only for a live session") and a concrete rule of thumb ("Read it before assuming a piece played"), plus an end-to-end workflow with update-session and the wait:'pass' loop. When-to-use and how-it-fits-with-alternatives are both covered.

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