get_discussion

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

Annotations already cover read-only, idempotent, non-destructive, open-world, so the safety bar is met without the text. The description adds genuinely useful behavior beyond them: a call-cost model ('1 call (2+ with include_items)', '+1 call per 500 items') and the fact that next_offset signals when to page — real operational context an agent needs.

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 resource and call cost, then return shape, then opt-in embedding, then sibling routing. Extremely dense with no filler; every clause carries a fact about identity, cost, return value, or alternative.

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 still enumerates what comes back (full body, topic_id, counters, url) and how paging works. For a 5-param read tool with full schema coverage and annotation coverage, nothing an agent needs to call it correctly is missing.

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, but the description adds cross-parameter behavior the schema cannot express: include_items embeds list_thread_items output as thread_items, and items_limit interacts with the returned next_offset for paging. id_or_key and strip_html semantics are left to the schema, which fully documents them.

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 ('One discussion by numeric id or short key') and immediately notes the single-item scope vs. the batched variant. It is instantly distinguishable from list_discussions, get_thread_markdown, and the create/update/delete 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?

Explicitly routes to two alternatives: get_thread_markdown for prose and list_discussions for a group's threads. The conditions are stated but in compressed telegraphic form ('Prose: get_thread_markdown'), leaving the agent to infer exactly when markdown beats the HTML body.

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