get_thread_markdown

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

Annotations already declare readOnly/idempotent/non-destructive, so the safety burden is lifted. The description still adds non-obvious behavior: the response is server-rendered Markdown with `markdown`/`chars`/`truncated`, and critically that `max_chars` cuts from the END so `truncated: true` drops newest items. It does not cover auth or rate limits, but for a read tool this is well above the annotation-covered bar.

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?

Two dense sentences, front-loaded with the primary use case and no filler. The packed parentheticals ('2 by discussion_id or poll_id; pass exactly one') are information-dense but slightly strain readability, keeping it just short of a 5.

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 compensates by naming the returned fields and the truncation flag; it also covers all four parameters, the id-selection rule, and the structured-data alternative. An agent has everything needed to call this correctly on the first attempt.

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 per-parameter meanings are already documented (baseline 3). The description nevertheless adds a cross-parameter constraint the schema cannot express — 'pass exactly one' of topic_id/discussion_id/poll_id — and reinforces the truncation semantics of max_chars, which is genuine added value.

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 and resource ('read/summarise this thread' returning server-rendered Markdown), and explicitly positions itself as 'the best single call' against the sibling list_thread_items for structured data. An agent can distinguish it from get_discussion and list_thread_items without opening any 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?

Explicit when-to-use ('for summarise / read this thread'), when to prefer another tool ('Structured data: list_thread_items'), the alternative ids with their cost ('+1 call'; 'prefer topic_id'), and the constraint 'pass exactly one'. Nothing about tool selection is left to inference.

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