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

Annotations only cover readOnlyHint/idempotentHint/destructiveHint; the description goes well beyond them by disclosing the idempotent-replay response shape ('idempotent_replay true'), the two auth modes with scope requirements, append-only immutability, and the deployment feature flag. The only omission is what a successful first-publish response looks like.

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 verb, resource and endpoint, and each subsequent clause carries required information (auth, refusals, idempotency, immutability). It is a single dense block of ~120 words, which is efficient but slightly hard to scan for the parameter list.

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 14-parameter mutation tool with no output schema, the description covers the critical gaps: authentication alternatives, idempotency/replay semantics, replacement path, refusal conditions, and the enabling flag. 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?

Schema coverage is already 86%, so the baseline is 3, but the description genuinely adds meaning the schema does not: idempotency_key becomes the signal's event_id, target_weight is a fraction of a follower's NAV, target_leverage is bounded by the vault's leverage cap, and rules_hash must be the CURRENT hash or the call is refused with the expected value. That is substantive semantic lift over 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 ('Publish a SIZED signal on a Forge vault you operate') plus the exact endpoint, immediately distinguishing it from siblings like forge_signal_plan and forge_signals. The qualifier 'SIZED' is a meaningful discriminator, not filler.

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 explicitly directs the agent to read rules_hash from forge_signals, explains the retry/supersede path via idempotency_key and supersedes_id, and lists the refusal conditions (paused vault, broken rule, hourly rate limit, disabled flag). When-to-use and when-it-fails are both spelled out rather than implied.

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