Scan network endpoints

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

Annotations already cover readOnly/idempotent/non-destructive/closed-world, so the bar is lower, and the description still adds real context: 'Requires: active-client', 'Produces: bounded-candidates', cost=high, and failure-handling guidance pointing to tool-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-loads the purpose in the first sentence and then uses compact labeled segments (Phase/cost/Requires/Produces/Safety/On failure). Nearly every clause earns its place, with only the redundant Signature line as minor waste.

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-required-param, no-output-schema scan tool, the description covers preconditions (active-client), cost profile, output shape hint (bounded-candidates), and failure recovery, leaving little an agent needs missing.

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 the schema already documents limit as a work budget and threadContext as a Roblox thread identity. The description's 'Signature' line merely restates the parameter names/types without adding semantics, 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?

States a specific verb and resource with scope: 'Find URL-like strings in function constants across getgc closures.' This lets an agent distinguish it from generic string search siblings like find-string-in-tables or search-gc-value, though it never names an alternative explicitly.

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?

No direct when/when-not statement or named alternatives among the many scan-*/find-* siblings. Usage is only implied via 'Phase: observe' and 'cost=high', which signal reconnaissance use but leave the choice between this and neighboring scanners to inference.

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