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

Annotations already establish that this is a safe read-only, non-destructive, non-open-world operation. Beyond that, the description adds useful behavior: query also searches transcripts, person narrows to exchanges with a contact, and results can feed draft_reply via attachment_ref. It does not cover pagination, ordering, or return shape, preventing a 5.

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 only two sentences and front-loads the main scope before the usage example. The first sentence is dense and contains an undefined term ('Quibblys'), but overall it is appropriately sized with little wasted language.

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 search tool with no output schema, the description covers the main attachment sources and the two filter parameters well. However, it omits limit/pagination behavior and does not fully describe the returned attachment objects beyond their use as attachment_ref values.

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 67%, with query and person already described in the schema. The description adds useful meaning for person by giving an example and explaining that it narrows to that conversation and to Quibblys sent to them, but it does not explain the limit parameter at all.

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 makes clear that this tool locates attachments that can be referenced by draft_reply, and it enumerates the sources: videos, voice notes, snippet files, and LinkedIn conversation files/images/GIFs. It distinguishes itself from draft_reply by naming attachment_ref, though it does not start with a direct verb like 'find' and leaves some terms such as 'Quibblys' unexplained.

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 a concrete usage pattern for the person parameter ('the file I sent Priya') and implies narrowing by conversation, but it does not explicitly say when to use this tool instead of siblings such as search_messages, list_library, or recent_messages. Usage is inferable rather than fully specified.

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