Code Assistant

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open-world), so the bar is lower, yet the description adds genuinely new context: the return surface ('text and proposed code') and the hard boundary that it does not touch files, execute commands, or mutate a repo. It omits auth, rate-limit, or latency details, but those are peripheral here.

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 dense sentences: the first front-loads the capabilities, the second covers output and scope limits. No filler, and the most decision-relevant information (what it does and does not touch) comes first.

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?

There is no output schema, so the description carries the return-value burden and discharges it ('returns text and proposed code'). Combined with the scope limits and action selection, an agent has enough to invoke it correctly; only finer detail like handling of very large files is absent.

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?

With 100% schema description coverage, the schema already documents every parameter including the action enum and its per-action params (error, focus, framework), so a 3 baseline is appropriate. The description only adds the meta-instruction to select an operation via 'action', which is minor incremental value.

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 specific verbs (explain, fix, refactor, generate tests) and a clear resource (code), making the tool's remit obvious at a glance. However, it never names the most likely alternative sibling (bee_chat) to distinguish a code-focused request from a general chat turn, so sibling differentiation is only implicit.

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?

'Use for code explanation, bug fixing, refactoring, or test generation' gives clear triggering contexts, and the negative clause ('does not read files, execute commands, or modify a repository') usefully bounds usage. There is no explicit when-not or named alternative, so it stops short of full routing guidance.

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