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

Annotations only declare readOnly/openWorld/no-destroy; the description goes much further, disclosing response clipping (description_max), per-part paging via limit/offset, the `more` continuation map, a reply size budget that truncates results, and that times are in the event's time zone. These are non-obvious behaviors an agent would otherwise discover only by trial.

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?

Content is front-loaded (what is returned first, then how to use it, then reply mechanics). It is one packed paragraph with deeply nested parentheticals that are slightly hard to parse, but no sentence is 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?

With no output schema and no annotations about returns, the description carries the full burden and does so: it names the response parts, explains paging and continuation, discloses truncation by description_max and by a size budget, and states the time zone. Nothing material is left for the agent to guess before calling.

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, but the description adds cross-parameter semantics the schema cannot: offset applies to all parts simultaneously, clipping is governed by description_max, and `parts` is the way to work around the size budget. It does not add much on `date` or `with_overlapping` beyond the schema, keeping it short of 5.

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+resource ('whole program of the event the API token belongs to') and enumerates the exact parts returned (halls, days, sessions, workshops, breaks, speakers, labels), including the type-0/type-1 distinction for sessions vs workshops. An agent can immediately tell this apart from the create_*/delete_*/list_* siblings.

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?

'Use it to read back ids (hall_id, speaker ids, label ids, session ids) before changing anything' gives concrete when-to-use guidance tied to the write siblings. It also prescribes a strategy for large events ('read one part at a time with `parts`'), but gives no explicit when-not-to-use or named alternative.

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