Diagnose a proxy error

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description still adds real value by disclosing the output character ('returns uncertainty and retry boundaries') and an input-hygiene constraint that annotations cannot express.

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?

Three short sentences, each earning its place: what to supply, what comes back, and what not to supply. Front-loaded with the actionable instruction and free of padding.

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?

An output schema exists, so return values need not be enumerated, and the description still signals the uncertainty/retry-boundary framing. Combined with annotation coverage and reasonably documented enum fields, an agent has enough to invoke it correctly, though the exclusion from sibling tools remains unstated.

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 coverage is 56%, and the description names only four of nine inputs (client, version, phase, status/exception) without adding format or interpretation detail. The schema's own field descriptions (normalized exception category, response provenance, bounded Retry-After) do the heavy lifting, so this is adequate but not compensatory.

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 (identify possible causes and the next check) on a specific resource (proxy errors) using named inputs. It is clearly distinguishable from doc-search and config-generation siblings, though it never names them 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?

Gives strong input guidance ('use structured client/version, phase, status or exception observations') and a negative constraint ('do not send raw logs, URLs or credentials'), which effectively tells the agent when this tool is inappropriate. However, it never contrasts with search_proxy_docs, get_proxy_doc, or generate_proxy_config, so the routing decision is left implicit.

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