get_context

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

Annotations only declare readOnlyHint=false, openWorldHint=true, destructiveHint=false; the description adds the key behavior behind the non-read-only flag by explaining that later calls return only what is new (i.e. the unread queue is consumed), plus an untrusted-peer-content warning. It does not state that events are permanently marked as read or whether that consumption is reversible, so it is strong but not complete.

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 short clauses, each earning its place: incremental semantics, the untrusted-data warning, and the polling instruction. The telegraphic fragment style ('Unread project events and the board') is slightly cryptic but wastes no words.

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 return values need no explanation, and `remaining` is referenced consistently with that. The incremental polling model, the `full` flag, and the trust boundary are all covered; only the ambiguous 'board' concept and any consumption/acknowledgement side effect are unaddressed.

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?

The single parameter has 0% schema description coverage, so the description must carry it, and it does: `full: true` means return everything rather than only what is new. The default (implicitly false) is only conveyed by contrast, leaving a minor gap.

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 names the resource returned (unread project events plus the board) and its incremental scope, so an agent knows this pulls team/project context rather than tasks or peers. It never states a verb and does not explicitly differentiate itself from siblings like list_tasks or list_peers, and 'the board' is left undefined, keeping it short of a 5.

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 concrete invocation guidance: call repeatedly while `remaining` is above zero, and pass `full: true` when everything (not just new items) is wanted. No alternative tool is named as a substitute, so it stops at 'clear context without exclusions'.

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