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

Annotations already declare readOnlyHint, openWorldHint, destructiveHint=false and idempotentHint=false. The description adds real behavioral context beyond those: the no-API-key oEmbed fetch, the exact pricing formula (virtual_quote_reserves / virtual_token_reserves), and critically the failure mode for graduated coins (it fails rather than returning a misleading zero). That failure disclosure is exactly the kind of context annotations cannot convey.

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?

Two sentences, front-loaded with the core purpose, then the method and the crucial graduated-coin caveat. The parentheticals (pricing formula, failure behavior) are dense but each earns its place because they define correctness of the result.

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 an analytical tool with no output schema, the description explains what is computed (a price delta over the window) but not the shape of the returned result. It covers safety via annotations and the failure mode well, yet leaves the agent guessing at the response structure.

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 75% (network has no description). The description reinforces windowMin (±window around post time) and adds a real constraint on mint beyond the schema's base58 note: the token must still be on its bonding curve. network and the post-time semantics remain undocumented, but the added meaning for the analytical parameters is genuine.

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?

The description states a specific verb+resource: correlate an X post to a memecoin's price impact, and even names the mechanism (oEmbed for metadata, pump.fun bonding curve for pricing). No sibling tool (e.g. social_cashtag_sentiment or get_bonding_curve) overlaps with this single-post impact measurement, so an agent can identify it immediately.

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 gives an explicit when-to-use condition ('measure how one X post moved a coin that is still on its bonding curve') and an explicit failure boundary ('a graduated coin has no curve, so the call fails'). It does not point the agent to an alternative tool for the graduated-coin case or for multi-post analysis, 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.