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

Beyond the annotations (idempotentHint, destructiveHint=false), the description discloses that it only adds and updates, that a forget request deletes nothing and returns to_forget and the named companies, that clients and non-fits are excluded from new results, and that it returns a short confirmation. That is substantial behavioral context an agent cannot get from the annotations alone.

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 scoping and mutation-safety information is front-loaded and every clause carries meaning, but the middle section is a long run of comma-separated examples that makes it slightly dense. Efficient overall, with minor rambling.

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 two-parameter, mutation-flagged tool with no output schema, the description covers the write scope, the refusal/deletion behavior, the effect on future results, and the return format ('a few words saying what was kept'). Nothing an agent needs 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 both parameters are already documented, including companies_on_screen's ordering for 'them'/'the second one'. The description reinforces the purpose of companies_on_screen for pronoun resolution but adds no syntax or format detail beyond the schema. Baseline 3 applies when the schema does the heavy lifting.

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 names a specific verb and resource ('Sharpens the rep's firm profile from what they say in passing') and enumerates the categories of facts it captures, so the agent knows it is a profile-update tool rather than a search tool. It distinguishes itself from the sibling 'forget' by explaining what happens on a forget request. Slightly indirect phrasing ('sharpens... from what they say in passing') keeps it from a crisp 5.

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 spells out when to use it – to record what the firm sells, device strengths, stage, geography, clients, or non-fits – and explicitly redirects a forget request to 'to_forget' behavior, so the boundary against the sibling 'forget' is clear. It stops short of stating exclusions for unrelated utterances or other alternatives.

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