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

Annotations already establish readOnlyHint=true, so safety is covered. The description adds substantive context the annotations cannot: performance fields appear only with explicit owner grant, exact quantities are separately permissioned, and broker account/credential/strategy identifiers are never returned. What is missing is pagination or result-size behavior for the list action.

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 summary plus per-action headings make it easy to scan, and each section earns its place. There is minor duplication where the opening sentence restates the 'lists approved account publications' line below it.

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-parameter, two-action read tool with no output schema, the description covers action routing, required fields, and the permission model governing returned data. The only meaningful gap is result-set behavior (pagination, limit/offset interplay) for action="list", which neither annotations nor schema describe.

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 coverage is 100%, so baseline is 3, but the description contributes conditional semantics the schema only gestures at: 'No other fields required' for list and 'Required fields: publicationId' for get, plus the global rule to send only the fields belonging to the chosen action. It still doesn't explain what mode/sort/query mean beyond their enum values, which the schema already carries.

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?

Both operations are named with a specific verb and resource: 'list' lists approved account publications, 'get' reads one permission-filtered account publication. The scope word 'public Marketplace' distinguishes it from the owner-side siblings (list_my_marketplace_publications, get_my_marketplace_publication) without ambiguity.

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 states the selection mechanism ('Set "action" to choose the operation. Only send the fields listed for that action') and names the required field per action, which is genuinely actionable routing guidance. It stops short of explicitly naming when to use this versus sibling tools like marketplace_strategies or the my-publications variants, so the agent must infer the public/private split.

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