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

With no annotations, the description carries full disclosure burden and mostly meets it by enumerating the exact return groups (protocol, chooser, never, grouped tools with when/avoid/example, tool_recipe_shapes, aliases). This tells agents the shape of the response and the routing semantics. It does not explicitly state read-only/no side effects, but the catalog framing makes mutation unlikely; a 4 rather than 5 because side-effect status and 'current turn' meaning are left implicit.

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?

Four sentences, front-loaded with the core purpose; the rest summarizes return data and usage in dense backticked terms. Every sentence earns its place, though the jargon (protocol, chooser, never) is not defined in prose — mitigated by the subsequent explanation.

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 3-parameter, all-optional catalog tool with an output schema, the description is largely complete: it covers what is returned, when to pass 'need', and that aliases exist. It could be more explicit about the meaning of 'teamshared' and 'current turn', but nothing essential for invoking the tool 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 coverage is 100%, and the schema already defines 'need' as a conversation router and 'tier'/'scope' as filters. The description adds only that 'need' should be passed mid-conversation, and shows the 'need → tool' mapping in the chooser. This is marginal beyond the schema, so a 3 is appropriate.

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?

Opens with a clear verb-resource pair ('Discover teamshared MCP tools') and a temporal scope ('for the current turn'). It immediately distinguishes itself from the sibling action tools: it is the meta-discovery/catalog tool, not a domain operation. The mention of return categories reinforces what the tool exists for.

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?

Gives one explicit usage rule: 'Pass need= when choosing a tool mid-conversation' — a concrete when-to-use condition. It does not list exclusion criteria or name alternative tools, but for a catalog tool the alternative set is all the tools it helps discover, so the guidance is sufficient.

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