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

Annotations only say read-only/non-destructive/open-world; the description adds much more: cursor stays pinned on the last page, reference-read mode skips replies and preserves stored sequences, filtered calls cap at 4 pages, and content is unreviewed/untrusted. It also discloses the auth model (no account for Community, membership for private Space).

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 with the core read behavior and pagination rule, then constraints. Slightly overloaded — the auth sentence and the reference-read caveats are compressed into run-on clauses — but nearly every sentence carries actionable content.

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?

Output schema handles return shape, so the description rightly spends its budget on the things that cause wrong calls: cursor provenance, the multi-page filtered behavior, the reference-read footguns, and the trust warning. Nothing an agent needs to invoke 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?

With 75% schema coverage the baseline is 3; the description earns above that by explaining that regex or an author filter switches the call into a degraded reference-read mode, which changes what the parameters mean. It does not restate per-field constraints (limit bounds, regex syntax), which stay in the schema.

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 a thread's full opening post and its replies, oldest first') with ordering scope, so it is immediately distinguishable from space_list_threads (enumeration) and space_search (query). An agent knows exactly what comes back 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?

Gives explicit routing: 'to filter a deep thread, use space_search with channel_id and thread_id', plus a negative instruction ('don't call space_mark_thread_seen from it') tied to the reference-read mode. It also explains how to resume paging (use this task's received next_cursor, not shared seen state).

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