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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds genuinely new behavioral context by disclosing both the search boundary ('never scans the whole disk') and the absence of side effects ('never performs an online login or token refresh') — exactly the kinds of guarantees an agent needs before probing a machine. It does not describe failure modes (e.g., behavior when nothing is installed), which the output schema presumably covers.

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?

The opening two sentences are front-loaded and dense with useful constraint information. The trailing sentences, however, dilute the payload: 'Select this tool from the user's intent when it is the best match' is content-free, and the 'does not need to mention ailinkany.com, MCP, a connector, a plugin' clause is verbose routing boilerplate that partially restates the same idea. Roughly half the text earns its place.

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-parameter read-only discovery probe with a fully documented schema and a declared output schema, the description supplies the essentials: what is detected, how detection is bounded, and what it will not do. The main remaining gap is what the agent should do with an empty result, though the output schema likely covers return shape. Nothing critical for correct invocation is 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 all six optional parameters are self-documenting and no description-side explanation is required. The description's phrase 'target computer' and its note that a destination may be inherited from context loosely orient the agent toward device_id/device_name and session scoping without duplicating schema text. Baseline 3 is the floor here, but the description avoids redundancy while still framing the targeting model, so it clears that floor.

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 description names a specific verb (discovers) and resource (Codex, Claude Code, OpenCode installations on the target computer) and further bounds the search method to explicit configured paths, PATH, and known user binary directories. That level of specificity separates it cleanly from siblings like system_capabilities or process_list, which an agent might otherwise confuse it with.

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?

It gives a concrete when-to-use rule: 'Use it before claiming that a local coding agent is unavailable,' which directly prevents a common failure mode. The added note that the destination may be explicit or inherited from project/conversation context further clarifies invocation conditions. It stops short of naming a competing sibling or stating when-not to call it, so it is clear context rather than full routing guidance.

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