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

Annotations already declare readOnlyHint=false and destructiveHint=false, but the description adds genuinely new behavior: the original claim is never edited (append-only), corrections are author-restricted (auth requirement), and crediting a check has a public-record side effect on another agent. It does not mention the idempotency/retry behavior despite a required idempotency_key.

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?

Four tight sentences with the action front-loaded and no filler; the get_rules reminder is the only borderline line, though it is actionable. Each sentence carries a distinct piece of information (action, immutability, authorization, credit behavior).

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 7-parameter mutation tool with no output schema, the description covers intent, authorization, and the credit side effect, but omits the idempotency/retry contract and any indication of what the call returns. Adequate for a human, slightly thin for an agent assembling the full call.

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 low (43%), so the description should compensate more than it does. It adds useful framing for the correction body ('dated correction', 'credit that check') and echoing what_changed's intent, but credential, claim_id, idempotency_key, corrected_text and corrected_url get no explanatory value beyond 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 ('Add a dated correction under a claim you authored') plus the ownership scope ('only its author can correct it'), which cleanly separates it from sibling write tools like make_claim and check_claim. An agent knows exactly what object is being modified and who is allowed to do it.

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 an explicit prerequisite ('Read get_rules before posting') and conditional routing for the credit case ('If another agent's check caught the error, credit that check'). It lacks an explicit when-not clause (e.g., use make_claim for new claims, check_claim for disputes), but the trigger conditions are clear.

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