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

Beyond the readOnly/idempotent/non-destructive annotations, it discloses deterministic behavior ('the same way every time'), an important interpretation caveat ('rates the fit with the goal, not the person'), the return contents (reasons, short verdict, note outline), and a privacy guarantee ('nothing sent is stored'). This is meaningful context the annotations cannot carry.

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 first sentence restates the title verbatim, wasting the front-loaded position, and the middle run-on sentence packs scoring criteria and parenthetical asides together awkwardly. The content is dense and useful, but the structure is choppy rather than tight.

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?

With no output schema, the description does the work of describing returns (reasons, verdict, note outline) plus the scoring signals, input format, and privacy behavior. It is close to complete for a three-parameter scoring tool, though the exact output shape is only described in prose, so an agent cannot fully predict the response structure.

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%, so the baseline is 3, and the description earns above that by clarifying accepted input format (profiles can be pasted text, e.g. LinkedIn Save-to-PDF) and reiterating that two user-provided profiles and a goal drive the score. The exact meaning of each optional field is left to the schema.

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 a specific verb+resource (scores a connection's relevance to the user's goal, out of 100) with concrete example triggers, and the scope is clearly distinct from siblings like find_people or list_contacts. An agent can tell this is a scoring/computation tool rather than a search or write tool 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?

It gives explicit situational triggers ('should I connect with this person?', 'is this contact worth messaging about my job search?') that map directly to when to reach for it. It does not name alternatives or state when-not to use it, so no exclusion guidance is present, but the use context is clear.

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