snapshot

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

Even though annotations already declare readOnly/idempotent/non-destructive, the description adds substantial context the annotations cannot: the exact return shape, the frame_ref staleness-guard semantics, the live signal fields (online/resolution/fps/format), and the unchanged_since_last_snapshot failure mode with an explicit 'do NOT trust them as ground truth' instruction. That is exactly the behavioral disclosure annotations cannot carry.

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?

Front-loaded with the core action, then organized into purpose, return contract, and caveat. Dense and mostly non-redundant, though the inline issue references (#143, #141) are low-value noise for an agent.

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?

There is no output schema, so the description must explain the return value, and it does: the [json_text, image] tuple, the frame_ref format, and the signal/unchanged fields. It also warns about the stale-frame edge case, leaving nothing critical for an agent to guess.

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?

Only one parameter (profile) and schema description coverage is 100%, so the schema already documents its meaning and default. The description adds nothing about profile or how it interacts with the returned frame, so the baseline 3 applies.

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?

Opens with a specific verb+resource ('Capture the current KVM screen') and immediately qualifies it with '(read-only)', which cleanly separates it from the actuating siblings like mouse, type_text and power. The return contract ([json_text, image]) further pins down what the tool produces.

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 downstream usage: pass the returned frame_ref to the mouse tool as observed_frame_ref, and explains why (absolute clicks refused after host reboot/media swap). It also tells the agent what to do when pixels look stale (check signal and logs). It does not, however, state when to prefer snapshot over the sibling classify_screen or wait_for_state, so the alternative-selection guidance is incomplete.

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