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

The description adds the critical withhold discipline (60 observed days before odds are given, accrued count stated) and 'Counted, never fitted' — behavior not present in the readOnly/idempotent hints. This explains how results are computed and why absence is not precision. The readOnlyHint is consistent with 'display-only context.'

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?

The description is appropriately sized and front-loaded, with each sentence covering a distinct aspect (what, how, withhold discipline, argumentlessness, state impact). Minor redundancy with readOnlyHint, but no wasted words.

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?

Despite no output schema, the description specifies the output contents (transition matrix, reach odds, accrued count) and the exposure threshold, making it self-contained for an agent to invoke. It could add exact output structure but is largely complete for a parameterless read tool.

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?

There are zero parameters, so per the baseline the description need not add parameter detail. It does state 'Takes no arguments,' which reinforces the schema's empty properties object.

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 description opens with a specific verb ('Read') and resource ('Markov forward odds for every state-bearing public-signal layer'), then details exactly what's returned: a transition matrix and empirical k-day reach odds. It clearly distinguishes from sibling tools by emphasizing 'Display-only context, never a state driver.'

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 provides clear context: use this to read empirical forward odds. 'Never a state driver' and 'Takes no arguments' signal when not to use it (for state changes or parameterized queries). However, it does not name a specific alternative tool among the siblings, so it lacks an explicit 'use X instead' pointer.

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