Create a listing (draft)

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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=false), and the description adds real value on top: it discloses that the effect is local-only persistence ('Stored locally; nothing is posted') and that it returns a ≤280-char drafted X post. It does not say what happens on repeat calls (duplicate/overwrite), 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?

Two dense sentences with no filler: the field inventory comes first and the return/side-effect statement follows. Efficient and front-loaded, though the field list is a long run-on that slightly obscures the two most decision-relevant clauses.

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?

With no output schema, the description correctly states the return (a drafted ≤280-char X post) and the persistence behavior, which covers the critical unknowns for a mutation tool. For an 18-param tool with nested objects and 0% schema description coverage, though, too many optional parameters are left entirely unexplained.

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 0%, so the description carries the burden and does add genuine semantics — notably 'private floor (lowest you'll accept) and ceiling' and 'photos (≤4 URLs/paths)', which clarify otherwise opaque fields. But of 18 params it only touches a subset (title/item, condition, ask, floor, ceiling, photos, pickup/delivery, payment, rules), leaving quantity, currency, location, highlights, category, style, tags and rule sub-fields undocumented anywhere.

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?

Specific verb (Create) + resource (sale listing) with the key content enumerated, and it implicitly separates itself from post_listing by stating 'nothing is posted' and calling the result a draft. An agent can tell this apart from post_listing/update_listing without opening the 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?

Usage is implied rather than stated: 'Returns a drafted X post... Stored locally; nothing is posted' tells the agent this is a draft-only step, which is a useful when-not signal for publishing. However, no sibling is named (e.g. post_listing for publishing, update_listing for edits), so the routing decision is left to inference.

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