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

Annotations declare the mutation profile (readOnlyHint=false, openWorldHint=true, idempotentHint=false), and the description adds substantial non-obvious behavior: processing is async, the call returns fast with status='pending', chunking/embedding happens in the background, and duplicate content is rejected. These async and dedup traits are not derivable from annotations or schema.

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?

Front-loads purpose, then the two modes, then processing behavior, then arg details, which is a logical order. It is somewhat long and the Args block partially restates the mode requirements already given in prose (content/url requiredness), a minor redundancy that keeps it just short of maximal conciseness.

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 6-param mutation tool with no output schema, the description covers mode selection, required inputs, async lifecycle, the polling path via get_knowledge, and failure conditions. An agent has everything needed to call it correctly and to handle the pending→ready/error transition.

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 only 17%, so the description carries the burden and does so well: it documents brand_id, source_type, content (with a ~50–100,000 token range and a ~200-character minimum), url (http/https, server-side fetch/extract), and name (default derivation). The only undocumented param, user_intent, has its own schema description, so nothing important is left ambiguous.

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 and resource ('Add a source to the brand's knowledge base') and immediately frames the domain ('knowledge is the brand-truth Trakkr feeds into AI-facing content generation'). This clearly distinguishes it from get_knowledge (read) and manage_knowledge (sibling mutation), so an agent can tell what it does without opening the schema.

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 enumerates the two modes (source_type='text' vs 'url') with the conditions and required fields for each, and states the dupe-rejection rule. It also routes the agent to the follow-up sibling: poll get_knowledge(brand_id, view='sources'). When-to-use is fully specified.

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