perch_stop

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

With no annotations, the description carries the full behavioral burden. "Close the browser session" implies teardown, but it does not say what state is destroyed, whether the call is idempotent when no session exists, whether it errors, or what "resume" actually preserves — that word alone is ambiguous about persistence.

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?

Two short sentences with zero filler, and the primary action is front-loaded before the follow-up instruction. Nothing in the text is redundant with the name.

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 zero-parameter teardown tool with no output schema, the description covers the essential action and the restart path. It falls short on the one thing an agent would genuinely want to know before tearing down a session — what happens to in-flight state and whether the close is destructive or reversible.

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?

The tool takes zero parameters, so per the rubric the baseline is 4. There is nothing for the description to disambiguate; the empty schema is fully consistent with the stated action.

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 (close) and resource (browser session), which cleanly separates it from the sibling family (read, edit, navigate, etc.). It references perch_start for the inverse operation, so the pairing is inferable, though it never explicitly contrasts itself with other lifecycle siblings like perch_status or perch_refresh.

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?

"Call perch_start again to resume" names the follow-up tool, which gives a partial sense of when this tool sits in a workflow. However, it never states the condition for calling it (session no longer needed, done browsing, cleanup after errors) nor any when-not guidance.

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