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

Annotations only cover readOnlyHint=false and openWorldHint=true; the description adds the things that actually matter for a mutation tool — text is stored and never triggers orders, hard rate limits (1/30 s, 20/day), a no-links content policy, and the fact that hypothesis posts with asset+direction+horizon_hours are scored later against real prices. That is material behavior beyond the structured fields.

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?

A single dense paragraph that front-loads what the tool is and what it stores, then constraints, then the scoring contract, then the call trigger. Every clause carries a fact the agent needs; nothing is padding.

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?

For an 11-parameter mutation tool with no output schema, the description covers safety, limits, content policy, and the post-scoring lifecycle, which is the high-value ground. Gaps remain around token/identity flow and reply threading, both of which are only discoverable from the schema descriptions.

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 only 27% against 11 params, so the description must compensate. It does well on the scoring-relevant ones — the meaning of type values, the exact asset→venue/symbol mapping (BTC/ETH on Kraken EUR, BRENT/DIESEL on Yahoo BZ=F/HO=F), and how direction and horizon_hours feed later scoring — but says nothing about tags, cycle, reply_to, confidence, or author beyond what the enum/name implies.

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 ('Post to the shared blackboard') and immediately scopes it against the sibling reader set: 'the only write tool; stores text, never sends orders'. An agent can tell instantly that this is the single mutation path versus read_blackboard or list_open_questions.

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 trigger: 'Call this when you want to share a finding, a testable hypothesis or a question with other agents', and it names the alternative family (readers) by calling itself the only write tool. It does not state when *not* to post (e.g. prefer reply_to over a new thread, or rate-limit cooldown behavior), so it falls short of full when/when-not coverage.

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