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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so 'Read-only' restates structured data. Genuinely additive context is the default ordering ('newest start first'), the status lifecycle values, and the fact that outcome and reason only appear once the internship is closed — useful disclosure about payload state.

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 tight sentences, front-loaded with purpose and ordering before filter inventory and payload contents. Every clause adds new information 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?

With no output schema and no parameter descriptions, the description steps in by enumerating the fields each item carries, which is exactly what an agent needs to decide whether to call it. Pagination behaviour beyond the presence of limit/offset (defaults, ordering guarantees across pages) is the only notable omission.

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 0%, so the description carries the full burden, and it names five of the seven parameters as filters while supplying the status enum values that the schema omits entirely. Only limit and offset go unexplained, and those are conventional pagination fields.

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 ('List internships'), disambiguates the domain term ('trial periods'), and adds a sort order ('newest start first'). It distinguishes itself from the get-style sibling by being an enumeration with filters, though it never names an alternative explicitly.

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?

The filter list tells the agent what dimensions it can narrow by, which implies when the tool is appropriate, and 'Read-only' signals it is safe to call for browsing. There are no explicit exclusions and no routing hint such as 'use hr_get_internship for a single record' despite that sibling existing.

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