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

Annotations only give the safety profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false); the description adds the actual return contract: writes return a summary of server-assigned facts plus a dashboard link, never the submitted object, and the matching get tool reads it back. That is meaningful disclosure an agent could not infer from annotations or schema.

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 prerequisites, then ambiguity handling, then the return contract — a sensible order with no filler. It is somewhat long and repeats the type-ambiguity paragraph that already lives in the schema, which costs a point.

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 nested, no-output-schema write tool it covers the critical gaps: it routes the agent to get_documentation and the schema tools for building valid commands, tells it where the result can be read back, and warns against duplicate creation. What it does not cover is validation (validate_script) or the shape of the commands array, though the pointer to the schema tools partly compensates.

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 50%, and the only parameter-level detail the description supplies (the HTTP/BROWSER/PLAYWRIGHT mapping plus the reuse caveats) is duplicated verbatim in the script property's schema description rather than adding new information. projectId, name, commands, and variables remain undocumented; the enum values themselves do get semantics from the description, which keeps this at baseline rather than below it.

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 and resource ('Create a new script in a project') and immediately disambiguates the three script types (HTTP=Protocol Bot, BROWSER=Browser Bot, PLAYWRIGHT=Playwright). It also distinguishes creation from the reuse/edit path, so an agent can separate it from update_script and duplicate_script without opening the schema.

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 when-to-use rules: read get_documentation and the schema tools before building commands, ask the user when 'browser script' is ambiguous, don't create multiple scripts of the same type per task, and reuse a previously created script for probes/retries. Prerequisites, exclusions, and the alternative path are all named.

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