Classify software-development task

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

Annotations already cover readOnly, idempotent, and non-destructive hints, so the description's job is to add context. It does so by listing the exact return JSON fields (task_type, deterministic confidence, protocol, matched_signals, alternative_task_types, ambiguous, recommendation), noting that confidence is deterministic, and describing the UNCLASSIFIED fallback when no reliable route is detected. This adds meaningful behavioral transparency beyond the annotations without contradicting them.

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 description is two sentences with zero redundancy. The verb and resource are front-loaded, the output contract is complete, and the usage guidance is placed at the end as a natural conclusion. Every sentence earns its place; nothing could be removed without losing information.

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 single-parameter classifier with no output schema, the description is fully complete. It enumerates the classification types, the fallback, and all return fields, and it tells the agent exactly when to invoke it (routing before loading workflow text). An agent has everything needed to call this tool correctly without further research.

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% with a clear description and examples, so the baseline is 3. The description adds a subtle but useful nuance by specifying that the input should be 'one concrete' task, which rules out abstract or multi-part descriptions. This is more than pure repetition of the schema and helps the agent choose appropriate input formatting.

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 clearly states that the tool classifies a software-development task into one of nine enumerated types (BUILD, DEBUG, etc.) or UNCLASSIFIED. The specific verb 'classify' plus the named resource and the explicit output categories distinguish it from sibling getter tools like get_anti_patterns and get_god_prompt, which retrieve data rather than classify. This is unambiguous.

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?

The description gives explicit usage context: 'use it for routing before loading detailed workflow text.' This tells the agent when to call this tool in a workflow. It does not explicitly name alternatives or state when not to use it, but the sibling tools are all getters with distinct purposes, so there is no real overlapping scenario. The guidance is clear but lacks an explicit 'when-not' clause.

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