mangome_observe

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

With no annotations, the description carries the full behavioral burden, and it only discloses that the tool is non-mutating ('never creates work identity or truth'). It says nothing about whether reads have side effects (e.g., BIGBANG_SCAN, RECONCILE_* operations sound stateful), permission requirements, or cost/latency characteristics.

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 with no filler, and the core claim is front-loaded. It is efficient, though the brevity comes at the cost of required detail rather than from trimming redundancy.

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 tool exposing 21 distinct operations with no annotations and an undocumented free-form payload, two sentences are substantially inadequate. The presence of an output schema justifies omitting return-value detail, but operation-level semantics and payload expectations are missing entirely.

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% with two parameters, one of which is a 21-value enum. The description adds no per-parameter meaning for 'operation' or the free-form 'payload' object, leaving the agent to infer which operation values exist and what payload shape each expects.

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?

The verb ('read/inspect') and resource ('derived or canonical context') are stated, so the broad intent is clear, but 'derived or canonical context' is abstract and the real semantics live in the 21-value operation enum. Nothing distinguishes it from siblings like mangome_query or mangome_status beyond the negative clause about work identity.

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?

There is no explicit when-to-use guidance. The only routing signal is the negative statement 'OBSERVE never creates work identity or truth,' which implies you should use a different tool for writes, but no alternative tool is named and no conditions for choosing among the 21 operations are given.

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