agy_project_read

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

Adds real value beyond the readOnly/idempotent annotations: no model call, sealed initial judgments withheld, provider sessions neither resumed nor authenticated. That tells the agent the operation is cheap and side-effect free and warns that some expected data will be absent. It does not cover pagination/limit behavior, which is the remaining gap.

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?

Front-loaded with the resource summary, then mode semantics, then behavioral caveats — a sensible order. It is dense and semicolon-chained, but nearly every clause carries distinct information; only the pagination aside is somewhat cryptic.

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-shape explanation is unnecessary, and the description correctly focuses on invocation modes and behavioral limits. For a six-parameter, multi-mode read tool the coverage is strong, though the unexplained limit and participant parameters leave a small hole an agent could stumble on.

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?

With 0% schema description coverage, the description carries the burden and does so for four of six params: project_id (omission lists projects), version (previous checkpoint), query (bounded public excerpts), sources (1..12 discussion_id#message_id). limit and participant are never explained — participant is only obliquely implied by 'participant views'.

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 specific verb+resource (read project memory) and enumerates exactly what is returned: durable memory, current plan, participant views, lifetime usage. It also draws a boundary by noting discussion history has separate message pagination, which distinguishes it from agy_discussion_read.

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?

Explicit mode-selection guidance is present: omit project_id to list projects, use version for a previous checkpoint, query for bounded excerpts, sources for exact originals. It never explicitly names a sibling to use instead, relying on the implicit 'discussion history has separate pagination' pointer rather than routing the agent outright.

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