Dock network

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

Annotations declare readOnlyHint=false and destructiveHint=true, but the description never explains why a capture tool is destructive (e.g., buffer clearing via the 'clear' param). It does add genuinely useful context beyond the annotations — secrets are redacted in returned URLs and the first call initiates capture — which earns partial credit.

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?

It is short and mostly front-loaded, and every clause carries information. However, the awkward first sentence ('Requests a tab made') undercuts readability and forces the reader to re-parse before the useful field list lands.

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 5-param tool with full schema coverage and no output schema, the description covers the returned fields and the capture-start behavior, which is adequate. It omits whether capture continues across calls, how 'clear' interacts with buffering, and any link to dock_tabs/dock_open beyond the schema's tab_id note.

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 description coverage is 100%, so clear/limit/failed_only/url_pattern are all documented in the schema. The description adds no parameter-level detail beyond noting URL redaction, 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?

The intent is inferable — it returns network requests captured from a tab, listing fields (url with secrets redacted, method, type, status, failures). But the opening phrase 'Requests a tab made' is garbled and the purpose has to be reconstructed rather than stated clearly. It also does no work to differentiate itself from siblings like dock_console or dock_status.

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?

There is no explicit when-to-use guidance and no alternatives named. The only usage signal is 'The first call starts capturing,' which hints at stateful behavior but doesn't tell the agent when to prefer this over dock_console or dock_status.

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