Search live Partner Center docs

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

Beyond annotations, the description discloses non-determinism ('results are not deterministic'), potential slowness, possible empty result with a note, retry safety, and no credential requirements. This enriches the readOnly/openWorld annotations with realistic failure and operational context.

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 concise, with no fluff. Each sentence contributes purpose, usage guidance, internet caveats, or return format. It is front-loaded with the core purpose.

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?

Covers purpose, when to use, behavioral traits, parameter nuances, and return shape ({ excerpts[], note }). Even though an output schema exists, the description summarizes it helpfully. No significant gaps given the tool's complexity.

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 already covers both parameters with descriptions, but the description adds 'Partner Center is prepended automatically, so do not repeat it' and notes that error codes/endpoint paths work as queries, plus explains topK omission behavior. This goes beyond the schema's baseline.

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 states the tool searches 'live Microsoft Learn Partner Center developer documentation' and returns 'matching excerpts', using a specific verb and resource. It clearly distinguishes from offline curated siblings by emphasizing 'live'.

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?

Explicitly instructs to try pc_list_scenarios / pc_get_scenario / pc_lookup_error first, and to use this tool as a fallback when the curated pack has no answer. This names concrete alternatives and gives both when and when-not to use.

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