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

Annotations cover the safety profile (readOnly, idempotent, non-destructive), and the description adds value beyond them: cost ('about 5 credits a head, so a three-way is around 15'), free no-op when fewer than two people are on file, and free candidate listing on ambiguous names. These billing and failure semantics are exactly the non-obvious traits an agent needs before invoking.

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 the core action and is generally efficient, but the opening enumeration ('how they work, how they come across, where their careers have gone...') and the triple example ('candidates for a role, people to pitch, names on a shortlist') are stylistically redundant. Every sentence still carries information, so the verbosity is tolerable rather than wasteful.

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 read-only tool with no output schema, the description supplies the return shape ('a table you can read down a column... or across a row'), cost, and failure modes, and the two parameters are fully covered by schema plus description. Nothing needed to invoke it correctly is missing.

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 100%, so the baseline is 3, but the description adds framing semantics for 'context' ('Tell it what the comparison is for and the framing follows') and reinforces the 2-5 cardinality of 'people' beyond the schema's minItems/maxItems. It does not add syntax detail for name-vs-object forms, which the schema already carries.

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 ('compare people side-by-side') and specifies the comparison axes (how they work, careers, experience, visibility, connections). It also distinguishes itself from lookup siblings by stating 'It compares people you have already looked up,' which an agent can use to separate it from enrich_person or get_dossier without opening a 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?

Gives clear context for use ('candidates for a role, people to pitch, names on a shortlist') and a prerequisite ('people you have already looked up'), plus edge behavior for fewer than two matches. It stops short of naming which sibling to use instead when people are not yet on file, so routing is implied rather than explicit.

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