message_log

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

With no annotations provided, the description carries the full burden. It clearly states this is a read operation ('Read'), and describes the kind of data returned (delivered, held, dropped). However, it does not disclose potential costs (e.g., large log sizes, performance implications), permission requirements, or any side effects. For a read-only log tool this is acceptable but not richly transparent.

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 two sentences, immediately states the primary purpose and the key filtering options. It is front-loaded with the most important information and has no filler. Every word contributes to understanding the tool's function and usage.

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 that all parameters are optional, no output schema exists, and the tool is a simple read operation, the description covers the essential aspects: what the log contains, how to filter, and that it reads rather than mutates. It could mention the default number of records or clarify that 'last_n' controls volume, but the schema already includes defaults and descriptions, so this is not a critical omission.

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?

The schema already provides 100% coverage for all three parameters (peer, last_n, thread), each with a description. The tool description reinforces these by mentioning 'Filter by peer' and 'follow a reply chain', which adds a little contextual meaning, especially for the thread parameter. But it doesn't add significant new semantics beyond what the schema already gives.

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 starts with a clear verb 'Read' and a specific resource 'Tin Can message log', and enumerates the core contents (what was sent, to whom, delivery status). It also highlights the two primary filtering modes (by peer or reply chain), which distinguishes it from the siblings 'peers' (listing peers) and 'send_peer' (sending messages) without confusion.

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?

The description implies when to use it: to inspect message history, filter by peer, or trace a thread. It does not explicitly state 'use this instead of peers or send_peer', but the verb 'Read' and the focus on log contents make the context clear. It lacks explicit exclusions, but the purpose is unambiguous enough for an agent to route correctly.

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