Search sessions

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

Annotations already carry readOnly/idempotent/non-destructive/closed-world, so the bar is lower. The description still adds real context beyond structured fields: these are vetted, reviewed marketplace listings, and the output is ids intended for subsequent tools. It does not describe pagination behavior, but that is minor given the annotation coverage.

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?

Two tight sentences, front-loaded with the primary scope and immediately followed by the return-value note. No filler, nothing redundant.

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?

For a 7-param, no-output-schema search tool, the description covers purpose, both scopes, and the return shape (ids for other tools). It omits pagination/sort hints, but the schema handles those, so nothing essential to correct invocation is missing.

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 only 43% (sort, tags, limit, offset undocumented), so the description must carry some weight. It reinforces the scope semantics ('reviewed marketplace listings' vs. 'your own saved sessions') but largely restates what the schema's scope description already says, leaving the four undocumented params untouched.

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 (Search) and resource (coding-agent sessions), and splits the resource into two clearly named modes: vetted marketplace listings vs. scope=library saved sessions. An agent can tell this apart from the fetch/get siblings without opening any 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?

Distinguishes the two operational modes (public marketplace, no sign-in vs. library needs library:read) and signals this is the entry point by noting it 'Returns ids to use with the other tools.' It stops short of explicit when-not-to-use guidance or naming the sibling that consumes those ids.

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