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

Annotations already declare readOnlyHint=true, idempotent and non-destructive, but the description adds genuinely new behaviour: the link renders client-side in the viewer's browser, offers Download and Share, and nothing is uploaded or stored server-side. That privacy/no-side-effect claim is the kind of context annotations cannot express, and it is consistent with readOnlyHint. It omits the cost/authorisation implications of step-based generation (viewer's own keys, ₹ confirmation) that live only in the schema.

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 short sentences, front-loaded with the transformation and its result, followed by what opening the link does and the no-storage guarantee. No filler and every sentence carries information an agent needs.

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 non-trivial tool with 12 parameters, nested objects and an output schema (so return values need no explanation), the description covers input modes, the resulting artefact and side-effect profile adequately. It falls short of fully complete because it gives no guidance on prerequisite or validation siblings and no hint about error behaviour for malformed plans or templates.

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 already 83%, so the baseline is 3; the description earns more by framing brief, template+fields, style+media and plan as alternative entry paths, which clarifies that most of the 12 parameters are mutually exclusive modes rather than a flat bag of options. It still does not state precedence when multiple modes are supplied at once.

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 concrete verb (turn ... into a link) plus the concrete artefact (a https://indiadigital.org/video/make/ URL) and enumerates the four input shapes that produce it: brief, template+fields, style+media, or plan. An agent can immediately tell this is the 'render a shareable video URL' tool rather than a planner or lister. It does not name the sibling tools (list_video_templates, get_edit_plan_schema, validate_edit_plan) that feed those inputs, so differentiation is implied rather than explicit.

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 four named input modes give clear, actionable context for how to invoke the tool depending on what the agent already has. There is no explicit 'when not to use this' and no routing to siblings such as validate_edit_plan before passing a plan, or list_video_templates to obtain a template id, which is a real gap for a 12-parameter tool.

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