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

Annotations already declare this is a non-read-only, non-destructive, closed-world write, so the description's job is to add consequence, and it does: the lesson counts towards a rule that goes live for every founder's agent once enough founders back it or an admin approves. It also adds a hard content constraint (no names, no identifying numbers) and "Free". It says nothing about validation failures or what happens to a duplicate submission, which keeps it off a 5.

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 what to record, then the privacy constraint, then timing, then the downstream effect. Dense and purposeful, though the enumerated trigger list is somewhat redundant with the `kind` enum already present in the schema.

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 a 9-parameter mutation tool with no output schema, the description covers the things an agent most needs: what qualifies, how to phrase it, how often, and what happens to it afterward. The gap is return feedback (success, dedup against sameAs, validation rejection), which the agent must discover by calling.

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 89%, so the schema already explains platform, rule, tried, happened, proofUrl and sameAs/against. The description reinforces the semantics of `rule` (must hold for any product, anonymized) and implicitly maps its trigger list onto the `kind` enum, but adds no field-level detail beyond that. Baseline 3 is right here.

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?

"Teach Shipfound's brain something this session showed" names a specific verb and resource, and the following clause enumerates exactly which events qualify (rejected/removed/flagged/banned, failed, worked better, founder correction). This separates it cleanly from siblings like record_action, notes_save and brain_review without the agent 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?

It states the trigger conditions precisely and gives a timing rule ("when it happens, not a summary at the end") plus a granularity rule ("one lesson per thing"). It does not name the adjacent alternatives (notes_save, record_action) that a confused agent might pick instead, so it stops short of full routing guidance.

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