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

Annotations already declare readOnlyHint=true and openWorldHint=true, covering the safety profile. The description adds useful behavioral context beyond annotations: it distinguishes capability urls (no password) from share urls (password required), which is an authentication detail. It does not cover error cases or return format, but with annotations the bar is lower.

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 front-loaded with the core action and resource before moving to usage guidance. The final sentence listing aliases adds some length but likely helps agents recognize the tool under alternative names. Overall it is efficient, though the parenthetical slightly interrupts the first sentence.

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?

Given the annotations (readOnly, openWorld) and the fully documented schema, the description covers what the tool does, when to use it, and the key authentication distinction. It does not explicitly describe the return format, but the schema's 'max_inline_bytes' field implies inline text content, and no output schema exists, so the description is largely complete for correct invocation.

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. The description still adds value by clarifying that the token can be either a capability url or a share url plus password, explaining the relationship between 'url_or_token' and 'password' that the schema only partially captures. The 'max_inline_bytes' parameter is not elaborated, but the schema documents it fully.

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 ('Fetch back') and resources ('durable memory', 'shared file/text') and names the source format (83blue url or token). It distinguishes itself from the storage sibling 'remember' and from generic fetch tools by tying recall to previously stored memory. An agent can identify the tool's function 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 provides clear usage contexts: recalling memory stored with 'remember' in an earlier session, or downloading a file another agent shared. It does not explicitly state when not to use the tool or name alternative tools like 'receive_file' or 'share_file', so it falls short of a full 5.

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