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

With no annotations, the description carries the full burden and does well: it discloses the OWNER tier requirement, the three accepted auth mechanisms, and the crucial non-side-effect property that findings do not trigger trades. It does not cover idempotency, deduplication, or what happens to a submitted finding downstream.

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 critical 'OWNER ONLY' constraint and stays dense with no filler, though it compresses several distinct concerns (auth, enums, thesis tie logic) into one long paragraph.

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?

An output schema exists so return values need no explanation, and the description covers auth, the kind taxonomy, and the counterthesis edge case. The remaining gap is the unexplained non-taxonomy params (confidence, mission, event_date), which is a meaningful omission for a 9-param tool.

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 0% across 9 params, so the description must compensate. It explains kind values, comma-separated symbols/sources, and gives detailed thesis_direction semantics including tie handling, but leaves body, title, mission, confidence, and event_date entirely unspecified.

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 ('submit a structured research finding into ... SharedBrain') and immediately ties it to a typed taxonomy (idea | anomaly | counterthesis | event), which separates it from submit_lesson, submit_daily_note, and submit_spaces_intel.

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 marks it OWNER ONLY and states that findings are context for analyst agents that never trigger trades, which tells the agent when this is appropriate versus direct action tools. It does not, however, name a sibling alternative or say when to prefer submit_lesson over submit_finding.

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