start_observation

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

The annotations only supply readOnlyHint=false and destructiveHint=false. The description adds meaningful behavioral context: it does not launch a timer, requires a follow-up poll_changes call, and needs an image-capable client for later review. This goes beyond the annotation hints without contradicting them.

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?

The description is three short sentences, each with a distinct role: core purpose, timer clarification, and client requirement. There is no filler or redundancy, and the most important info is front-loaded.

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?

The tool has no output schema and two optional parameters that are unexplained. While the description covers the overall workflow, an agent cannot determine what duration_seconds vs. interval_seconds control or what the call returns, which is a significant gap for a tool with schema coverage of 0%.

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% and the description never mentions duration_seconds or interval_seconds. There is no explanation of how these settings affect the baseline capture, leaving all meaning to be guessed from parameter names and defaults.

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 opens with 'Capture baseline for the locally verified contact' – a specific action and target resource – and explicitly notes 'never reply to baseline history.' It also distinguishes itself from poll_changes by stating it does not launch a timer, making the tool's role clear among siblings.

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 direct sequential guidance: after this tool, 'The MCP client must call poll_changes.' It also sets a clear prerequisite ('Requires an image-capable client') and a behavioral restriction ('never reply'). It stops short of naming alternative observation-related tools or stating when not to use it.

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