tandem_overview

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

With no annotations, the description carries the full burden and does a decent job: it declares the tool is a pure observation, enumerates four side effects it does NOT perform (claim acquisition, permission grants, reconciliation, restart), and notes the result set is paged. It omits any statement about permissions/access requirements or what the returned inbox entries look like, which keeps it short of 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?

Three short sentences with the read/paged scope front-loaded, which is good. However, 'Follow exact reader descriptors for complete evidence' is vague filler that consumes a whole sentence without conveying actionable information.

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?

An output schema exists, so return values need not be explained and the safety profile is well covered. What is missing is pagination mechanics for the two undocumented parameters and any indication of access prerequisites, leaving an agent to guess how to page through the inbox.

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% for two parameters, so the description must compensate and it largely does not. The word 'paged' hints that cursor/limit control pagination, but there is no explanation of cursor format, where a cursor comes from, or what limit bounds — 'Follow exact reader descriptors' is not a substitute for that.

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 ('Read') and resource ('this project's paged inbox of questions, results and recovery needs'), which is specific enough to picture the payload. It does not explicitly contrast itself with siblings like tandem_read_result or tandem_list, and the phrase 'reader descriptors' is opaque jargon that adds no clarity.

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?

Usage is implied ('read this project's ... inbox') rather than stated as a when-to-use rule, and no sibling is named as the alternative. The negative clause ('never acquires a claim, grants permission, reconciles or restarts execution') does implicitly route mutating work elsewhere, which is the only real guidance present.

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