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

Annotations already declare readOnly=false, destructive=true, idempotent=false, so the safety profile is carried by structured data. The description adds a genuinely non-obvious operational fact: 'The client opening the same link sees the new version,' i.e. edits publish live to the client. It stops short of warning that removals/replacements are irreversible, which matters for a destructive tool.

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 sentences, front-loaded with the core identity ('edit existing, keep link') before the operation list. The semicolon-delimited enumeration is dense with zero filler.

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 10-parameter, deeply nested mutation tool with no output schema, the description covers every editing mode and the client-visible consequence. It leaves out the required report identifier, error/partial-failure behavior, and any irreversibility caveat, so it is strong but not fully 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?

With 80% schema coverage the baseline is 3, but the description adds an intent-to-parameter mapping that is easy to scan: title/period/client label, 'replace all sections' (sections), 'replace or add some' (replace_sections/add_sections), 'remove sections by heading' (remove_headings), 'change the look (style)'. It omits clear_style entirely, leaving one mutating parameter unmentioned.

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 and resource ('Edit a report') and immediately differentiates from siblings by scope: 'that already exists and keep its link.' An agent can distinguish this from create_client_report / create_prospect_report without inspecting either schema.

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 precondition is explicit ('a report that already exists and keep its link'), and the enumerated edit modes give clear context for the situations the tool covers. It never names create_client_report as the alternative for new reports, so there is no explicit when-not guidance.

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