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

Annotations already declare readOnlyHint=true and destructiveHint=false, but the description adds substantial context: it returns counts plus a file name and size, never content, and changes nothing. It also discloses exactly what the optional check does (identifies the app, performs a test save and read back that is left nowhere and sent to no one, lists connected apps with last-seen times), which is behavior an agent could not infer from 'readOnly'.

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?

Purpose and return shape are front-loaded, then usage, then the check semantics, which is a sensible order. It is a dense single block and the check section is longer than strictly necessary, but each sentence carries load-bearing information and nothing is padding.

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 carries the return-value burden and does so: status categories, count-level granularity, and the file name/size disclosure boundary. Combined with the check behavior and the explicit no-side-effects statement, an agent has everything needed to call it correctly and describe results to a user.

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 100% and the boolean 'check' is already documented, so the baseline would be 3. The description goes beyond that by explaining what the check actually does, what it produces, and the conditions under which it should be enabled, which is meaningful semantic guidance for an otherwise opaque flag.

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 (see what happened to sent context) and enumerates the exact outcome states: still waiting, picked up, taken back, expired. That vocabulary cleanly separates it from siblings like pick_up_context, take_back_context, and send_context, which are actions on context rather than a status report.

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?

Gives explicit triggers ('when your person asks whether their other app got it'; 'when your person asks whether Oyeh is working'), a conditional trigger tied to a first_time answer, and an explicit prohibition ('never on your own'). Both the default path and the check path have clear when-to-use rules.

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