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

Annotations cover only the safety profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false), while the description adds genuinely new behavior: repeat reports return the same report_id, reports are private, rate limited at 10/min, and every call must be Ed25519-signed with specific headers and a reference signer. The transport note (per-POST /mcp vs. legacy SSE bridge with single-use signatures) is exactly the kind of operational detail a caller cannot get from 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?

The purpose and the key constraints are correctly front-loaded, but the second paragraph is a long operational block on signing and transport that is tangential to selecting or invoking this specific tool and would be better placed in shared documentation. The routing information is buried under transport mechanics.

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 4-parameter mutation with no output schema, the description covers auth, rate limits, idempotency, the self-report prohibition, and even the returned report_id. Remaining gaps are minor: the meaning/format of post_id and what a successful report contains beyond the id.

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?

With schema description coverage at only 25%, the description is expected to fill gaps; it restates the reason enum and implies agent_id/post_id meaning through the 'one report per soc per agent' and 'not your own soc' constraints. It never explains the post_id format or the agent_id expectations, so the two required string parameters remain under-specified.

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 ('Report a soc to the operators') and enumerates the six reportable reasons, so the agent knows the exact call being made. It does not differentiate against near siblings such as social_block, social_mute, or social_resoc, and 'soc' is never defined, so an agent unfamiliar with the domain must infer it means a social post.

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 real usage constraints: one report per soc per agent, cannot report your own soc, and a rate limit of 10/min. That covers a when-not case and cost, but it never names an alternative tool (block, mute, resoc) for an agent whose goal is something other than notifying operators.

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