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

Annotations already cover readOnly/idempotent/destructive, so 'Changes nothing' largely restates them, but 'Needs the user's account' adds a genuine auth prerequisite not present in structured fields. It still omits ordering, pagination, and how the default limit behaves.

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?

Four short sentences, trigger front-loaded, with no filler. Every clause either routes usage, describes output, or flags a prerequisite.

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 usefully enumerates returned fields (status, recipient, price, tracking number) and notes the account requirement. It is thin on result-set size and ordering, which matters for a list tool with a capped default.

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 0%, so the description must carry parameter meaning. It explains the optional status filter, but the limit parameter (default 10, max 50) is never mentioned, leaving result-count behavior undocumented.

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 concrete verb+resource ('see their recent letters') and implies a collection rather than a single letter, which separates it from get_letter. It stops short of naming any sibling explicitly, so an agent must infer the list-vs-get boundary.

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?

'Use this when the user wants to see their recent letters' gives a clear triggering condition, and 'optionally filtered by status' clarifies the variant case. No when-not conditions or named alternatives (e.g. get_letter for a single letter) are provided.

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