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

With no annotations, the description carries the behavioral disclosure burden. It adds useful context: the data is curated, rows publish only on evidence, replacements are blank when IBM has not named one, and the data mirrors assetize.com.au. This gives an agent a realistic picture of data provenance and quality.

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 a single dense sentence with no filler. It front-loads the core content (what, for which product, what versions, replacement, evidence) and then adds the curation caveat and external-source equivalence, all in one efficient statement.

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 simple one-optional-parameter lookup with no output schema, the description covers the record fields and data quality behavior. It stops short of stating the return shape explicitly, but the field-level enumeration makes the expected output understandable.

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?

The only parameter, 'kind', is fully documented in the schema with allowed values DEPRECATION, REMOVAL, or RENAME. Since schema coverage is 100%, the description does not need to add parameter-level detail, meeting the baseline.

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 clearly states the tool returns a curated register of deprecations, removals, and renames for Maximo/MAS, including version, replacement, and evidence. It distinguishes itself from generic changelog or record tools, though it lacks an explicit imperative verb like 'get' or 'list.'

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 usage context is implied: use this when you need deprecation, removal, or rename facts with evidence. However, it does not explicitly say when to use this versus sibling tools like maximo_changelog or records_by_version, nor does it mention any exclusion criteria.

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