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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds genuinely non-obvious behavior: result times are rendered in the event's local timezone, and event_id is a UUID sourced from search_events. It does not mention pagination behavior for `list_sessions`, which is the only real omission.

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-loaded purpose sentence followed by one bullet per action, each a single clause pair of what it returns and what it filters on. Prerequisites and the sibling pointer are packed into the trailing two sentences 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?

All five action branches are covered, prerequisites are stated, and the output schema plus read-only annotations carry the return-shape and safety burden. The only gap is that `page` exists on list_sessions but the description never indicates results are paginated or how to iterate them.

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 100%, so the baseline is 3; the description goes further by binding parameters to actions (track/category/location/date as filters, `query` matches session titles, `session_id` mandatory for get_session). It does not add format detail beyond the schema, so it is an increment rather than a full 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?

The opening sentence names the specific resource (agenda data) and its scope (a single event), then enumerates all five `action` values with what each returns. An agent can distinguish this read tool from siblings like create_sessions, update_session, delete_session, or read_speakers without opening the schema.

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 per action: use `metadata` to obtain track/category/location/date filter values, `list_sessions` for searching and filtering, `get_session` when a session_id is known. It also names the escape hatch to a sibling ('For speakers, use `read_speakers`') and the upstream prerequisite (event_id from search_events).

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