update_connection

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

With no annotations, the description bears the full burden and does substantial work: it discloses that null deletes a field, that ssh merges field-by-field rather than replacing wholesale, and that queryTimeoutMs controls the per-request deadline with null restoring the 60 s default. Undisclosed: permission requirements, behavior when the named connection is missing from both layers, and whether changes take effect on live connections.

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?

Three dense sentences, front-loaded with the verb and scope, then the mutation semantics, then the one non-obvious field. The inline JSON examples earn their place, though the sentence structure is somewhat crammed with parentheticals.

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 nested-object mutation with no annotations and no output schema, the merge/delete semantics are well covered, but return behavior (does it return the updated connection?) and failure modes (connection not found, invalid hostKey pattern, conflicting ssh fields) are absent. An agent knows how to shape the patch but not what to expect back.

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 compensate; it explains the null-deletion convention, the nested ssh merge rule, and queryTimeoutMs semantics, which covers the trickiest parts. However, the patch object contains a second `name` field (rename, with its own regex) that the description never mentions and whose relationship to the top-level `name` identifier is left ambiguous; port, user, scheme, apiKey, verifyTls and readonly are also unaddressed.

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?

Specific verb+resource: 'Patch an ES connection by name', plus the scope clarification that it applies to the layer the connection lives in (project or global). This distinguishes it from add_connection and remove_connection without naming them explicitly, though a direct sibling reference would have sealed a 5.

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?

Usage is implied by the word 'patch' (partial update of an existing connection, not creation), but there is no explicit 'use this instead of add_connection when...' or prerequisite guidance. The null-removal example describes mechanics rather than when to choose this tool over test_connection or add_connection.

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