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

Despite annotations already covering the safety profile (readOnlyHint/destructiveHint/openWorldHint), the description adds substantial behavioral context: page sizes (1000 rows / 256KiB), oversized_row handling, the truncated=true→cursor continuation rule, and the mmp_not_enabled error condition, plus an explicit 'No writes' confirmation. This is rich, non-redundant disclosure.

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 dense sentences with no filler; the what/scope leads, followed by paging mechanics and the error condition. Slightly information-heavy, but every clause earns its place and nothing is buried.

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?

With no output schema, the description does the work of describing return content, paging, and the error sentinel, which is appropriate for a 2-param read tool. The one remaining gap is the unexplained connection_context parameter, so it falls just short of complete.

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%, so the description must carry parameter meaning. It explains cursor well (pass next_cursor back as cursor when truncated=true), but connection_context is never mentioned in the description — only its format is implied by the schema pattern. Half the parameters remain semantically undocumented.

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 ('Read') and enumerates the resources (MMP connections, synced apps, event mappings, cohort configs), scoped to the current user. This clearly distinguishes it from siblings like mmp_fetch_cohorts, mmp_save_cohort_config, and mmp_delete_connection, which an agent can rule out without opening schemas.

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?

Implied usage is clear (read the current user's MMP state), but the description never says when to prefer this over mmp_fetch_cohorts or when to call it versus the connection-mutation siblings. It also gives no prerequisites beyond the tenant-level mmp_not_enabled note, leaving alternative selection to inference.

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