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

Annotations already declare this is a non-read-only, non-destructive, non-idempotent write, so the description need only add context — and it does: it says the record is scoped to the authenticated user, that a description body is persisted, and that an id is returned for downstream calls. What it does not address is what happens on a duplicate save (idempotentHint is false, so an agent might wonder if re-saving creates a second listing) or any auth/permission failure modes.

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?

Three sentences, each doing distinct work: what it saves, when to use it, and how the result chains into other tools. The purpose and the sibling disambiguation are front-loaded with no filler.

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?

An output schema exists, so not explaining the return shape is fine, and the description still notes the returned id is what feeds jobListingId downstream. For a simple two-object write tool the coverage is nearly full; only duplicate-handling and auth requirements are left implicit.

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 reported as 0%, so the description should carry more of the parameter burden. It conveys intent at a high level (company + role + description), which maps onto the nested company.name / listing.position / listing.description structure, but it never names the nested fields or notes that company and listing are required objects with additionalProperties:false, so an agent still has to read the schema carefully.

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 and resource ("Save a manual job listing for the authenticated user") and even names the underlying endpoint POST /api/job-listings. It immediately distinguishes this write tool from the read siblings get_user_job_listing and list_user_job_listings.

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 trigger ("Use when the user wants to store a company + role + description for later cover letters") and explicitly routes the agent elsewhere for reading stored data, including the non-obvious caveat that list_user_job_listings will not return the description. Downstream chaining to get_cover_letter_cost / create_cover_letter is spelled out.

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