network_get_requests

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

Wit no annotations, the description carries the full disclosure burden and does so well: it reveals the capture-boundary limitation, explains that response bodies are excluded by default 'because they are large', and offers the reload remedy. The read-only nature is implied by 'List' with no hidden mutating effects. Minor omission: no statement about pagination/ordering behavior, though the schema covers offset semantics.

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?

Four sentences, each earning its place: core purpose, filter modes, body-size caveat, and capture boundary with a remedy. The verb+resource is front-loaded in the first word. There is no filler and no redundant restatement of schema content.

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?

For a read tool with 11 parameters and no output schema or annotations, the description covers purpose, returned fields, filter modes, and the key trap (capture start), so an agent can call it correctly without further research. It could add a pointer to network_get_response_body for full bodies, but include_bodies largely fills that role.

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%, putting the baseline at 3, but the description adds real value beyond the schema: it groups the filter dimensions ('Filter by URL substring, method, status or failures only') and explains the rationale for include_bodies being opt-in ('because they are large'), naming the parameter directly. That pushes it a step above baseline.

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 and resource — 'List HTTP requests captured since attach' — and enumerates the returned fields (method, status, duration, size, initiator). The listing verb disambiguates it from siblings like network_clear, network_wait_for_request, and network_get_response_body, and the filter sentence adds further scope. Nothing ambiguous remains about what the tool does.

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 final sentence gives actionable context: 'Capture starts when DevCDP attaches, so requests from before that are not here — reload to see them.' This tells an agent why prior requests may be absent and how to remedy it. It does not explicitly name alternatives such as network_wait_for_request or state when-not-to-use this tool, so it stops short of full routing guidance.

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